Can you tell when an AI model is lying? Announcing Aletheia's Quest, an AI lie detection challenge running this summer, organized by Cadenza Labs and NDIF. Multiple model organisms to interrogate and probe, $50K prize pool, no local GPU required.

NNsight 0.6 is out now! We directly address your feedback in our biggest release yet. Pain points included cryptic errors, slow traces, no remote execution of custom code, and limited vLLM support. We tackle all of these and more in this new release. 🧵 Here's what changed:

Watch Sam Marks present his work "Auditing Language Models for Hidden Objectives" in our new YouTube video! Sam's team ran a blind auditing game to assess efficacy of black box and white box techniques for LLM alignment auditing. 🔗 youtu.be/jZiOJTHqB6M

Auditing Language Models for Hidden Objectives with Sam Marks

Sam Marks leads Anthropic's Cognitive Oversight team, a subteam of Alignment Science. Sam's research focuses on settings where understanding something about ...

youtube.com

Check out the NDIF & Bau Lab lightning talks at the NeurIPS 2025 Mechanistic Interpretability Workshop (mechinterpworkshop.com/): youtube.com/playlist?li...

NeurIPS 2025 Mechanistic Interpretability Workshop

Talks from NDIF and Bau Lab at the NeurIPS 2025 Mech Interp Workshop

youtube.com

New YouTube video posted! @benjaminfeuer.bsky.social discusses LLM's annus mirabilis, presenting his work on open questions surrounding LLM judges, benchmark trustworthiness, and maximizing the potential of synthetic data. Watch here: www.youtube.com/watch?v=pehc...

Annus Mirabilis: A Year of Explosive Progress in LLMs with Benjamin Feuer

YouTube video by NDIF Team

youtube.com

🔥I am super excited for the official release of an open-source library we've been working on for about a year! 🪄interpreto is an interpretability toolbox for HF language models🤗. In both generation and classification! Why do you need it, and for what? 1/8 (links at the end)

New year, new YouTube videos! We are resuming our regular interpretability seminar posts, with a fantastic talk by Deepti Ghadiyaram on interpreting diffusion models. Watch the video: youtu.be/4eqvABPX5rA

Interpreting and Leveraging Diffusion Representations with Deepti Ghadiyaram

Deepti Ghadiyaram is an Assistant Professor at Boston University in the Department of Computer Science, with affiliated appointments in Electrical and Comput...

youtube.com

So excited to have you on the team, @gsarti.com!

Gabriele Sarti@gsarti.com · 8mo ago

📣 I'm starting a postdoc at Northeastern University, where I will work on open-source NN interpretability with @davidbau.bsky.social and the @ndif-team.bsky.social. In 2026, we'll grow the NDIF ecosystem and democratize access to interpretability methods for academics and domain experts! 🚀

nnterp by @butanium.bsky.social is now part of the NDIF ecosystem! nnterp standardizes transformer naming conventions, includes built-in best practices for common interventions, and is perfectly compatible with original HF model implementations. Learn more: ndif-team.github.io/nnterp/

Happy Holidays from NDIF! Our new NNsight version improves performance and enhances vLLM integration, including support for tensor parallelism.

What does an LLM do when it translates from Italian "amore" to Spanish "amor" or French "amour"? That's easy! (you might think) Because surely it knows: amore, amor, amour are all based on the same Latin word. It can just drop the "e", or add a "u".

Making model internals accessible to domain experts in low-code interfaces will unlock the next step in making interpretability useful across a variety of domains. Very excited about the NDIF Workbench! 💡

NDIF Team@ndif-team.bsky.social · 11mo ago

Ever wished you could explore what's happening inside a 405B parameter model without writing any code? Workbench, our AI interpretability interface, is now live for public beta at workbench.ndif.us!

Ever wished you could explore what's happening inside a 405B parameter model without writing any code? Workbench, our AI interpretability interface, is now live for public beta at workbench.ndif.us!

New YouTube video posted! @wendlerc.bsky.social presents his work using SAEs for diffusion text-to-image models. The authors find interpretable SAE features and demonstrate how these features can alter generated images. Watch here: youtu.be/43NnaqGjArA

Interpreting SDXL Turbo Using Sparse Autoencoders with Chris Wendler

In this talk, Chris Wendler presents his recent work on using sparse autoencoders for diffusion models. In this work, they train SAEs on SDXL Turbo, finding ...

youtube.com

Reminder that today is the deadline to apply for our hot-swapping program! Be the first to test out many new models remotely on NDIF and submit your application today! More details: ndif.us/hotswap.html Application link: forms.gle/KHVkYxybmK12...

NSF National Deep Inference Fabric

NDIF is a research computing project that enables researchers and students to crack open the mysteries inside large-scale AI systems.

ndif.us

Want increased remote model availability on NDIF? Interested in studying model checkpoints? Sign up for the NDIF hot-swapping pilot by October 1st: forms.gle/Cf4WF3xiNzud...

NDIF Hot-swapping Beta Testing

Do you have a research project where you plan to study many different models? NDIF will soon be deploying model hot-swapping, which will enable users to access any HuggingFace model remotely via NDIF....

forms.gle

DDavid Bau@davidbau.bsky.social · 11mo ago

Announcing a broad expansion of the National Deep Inference Fabric. This could be relevant to your research...

Do you wish you could run experiments on any model remotely from your laptop? In a future release, NDIF users will be able to dynamically deploy any model from HuggingFace on NDIF for remote experimentation. But before this, we need your help!

We are presenting our NNsight / NDIF demos at NEMI now! Tune in: youtube.com/live/q8Su4C...

New England Mechanistic Interpretability Workshop

09:30 AM - 09:40 AM: Opening Remarks (David Bau) 09:40 AM - 10:00 AM: Keynote 1: Lee Sharkey: "Mech Interp: Where should we go from here?" 10:00 AM - 10:10 A...

youtube.com

The NEMI conference is live! Watch our livestream here: youtube.com/live/q8Su4C...

NEMI 2025

youtube.com

This Friday NEMI 2025 is at Northeastern in Boston, 8 talks, 24 roundtables, 90 posters; 200+ attendees. Thanks to goodfire.ai/ for sponsoring! nemiconf.github.io/summer25/ If you can't make it in person, the livestream will be here: www.youtube.com/live/4BJBis...

New England Mechanistic Interpretability Workshop

About:The New England Mechanistic Interpretability (NEMI) workshop aims to bring together academic and industry researchers from the New England and surround...

youtube.com

Announcing a deep net interpretability talk series! Every week you will find new talks on recent research in the science of neural networks. The first few are posted: jackmerullo.bsky.social, Roy Rinberg, and me. At the @ndif-team.bsky.social Youtube Channel: www.youtube.com/@NDIFTeam

NDIF Team

We're a research computing project cracking open the mysteries inside large-scale AI systems. The NSF National Deep Inference Fabric consists of a unique combination of hardware and software that provides a remotely-accessible computing resource for scientists and students to perform detailed and reproducible experiments on large pretrained AI models, such as open large language models. We aim to make AI interpretability research more accessible through this channel by publishing lectures and educational content covering real interpretability research.

youtube.com

Our YouTube channel is live! Our first video features @davidbau.bsky.social‬ presenting the ROME project: www.youtube.com/watch?v=eKd...

ROME: Locating and Editing Factual Associations in GPT with David Bau

David Bau is an Assistant Professor of Computer Science at Northeastern University's Khoury College. His lab studies the structure and interpretation of deep...

youtube.com

Induction heads are attention heads that help complete patterns by copying tokens (transformer-circuits.pub/2021/framew...), but can they also copy over concepts?

Great to present what’s coming next for NDIF at the @actinterp.bsky.social workshop at #ICML2025! If you missed us, let’s chat after the conference. Reach out here: forms.gle/LtTyYnkaxDyg...

We’re excited to announce a new series of applied "mini paper" tutorials! The goal of this series is to help researchers get hands-on experience with findings, methods, and results from recent papers in interpretability using NNsight and NDIF.

Excited to share our first paper replication tutorial, walking you through the main figures from "Do Language Models Use Their Depth Efficiently?" by @robertcsordas.bsky.social 🔎 Demo on Colab: colab.research.google.com/github/ndif-... 📖 Read the full manuscript: arxiv.org/abs/2505.13898

Google Colab

colab.research.google.com

We are prereleasing NNsight 0.5 today! We've added many highly-requested new features, including easier access to intermediate values within the forward pass, ability to run any code within NNsight’s tracing context (no more proxies!), and easier debugging.

Are you interested in researching diffusion models in NNsight? We've released our first non-LLM tutorial, which covers the Diffusion Lens technique!

At #ICLR2025 in Singapore? Come visit our poster tomorrow (Saturday, April 26th)! This work addresses a critical gap in ML research: the ability to study the internals of very large neural networks.

What will be the linchpin for AI dominance? Read our NSF/OSTP recommendations written with Goodfire's Tom McGrath tommcgrath.github.io, Transluce's Sarah Schwettmann cogconfluence.com, MIT's Dylan Hadfield-Menell @dhadfieldmenell.bsky.social TLDR; Dominance comes from **interpretability** 🧵 ↘️