🔥Telegram İfşa

1/13 LLM circuits tell us where the computation happens inside the model—but the computation varies by token position, a key detail often ignored! We propose a method to automatically find position-aware circuits, improving faithfulness while keeping circuits compact. 🧵👇

Lots of progress in mech interp (MI) lately! But how can we measure when new mech interp methods yield real improvements over prior work? We propose 😎 𝗠𝗜𝗕: a Mechanistic Interpretability Benchmark!

I'll be presenting this in person at NAACL HLT 2025, tomorrow at 11am in Ballroom C! Come on by - I'd love to chat with folks about this and all things interp / cog sci!

Our interpretability team recently released research that traced the thoughts of a large language model. Now we’re open-sourcing the method. Researchers can generate “attribution graphs” like those in our study, and explore them interactively.

The methods we used to trace the thoughts of Claude are now open to the public! Today, we are releasing a library which lets anyone generate graphs which show the internal reasoning steps a model used to arrive at an answer.

We’re releasing an open-source library and public interactive interface for tracing the internal “thoughts” of a language model. Now anyone can explore the inner workings of LLMs — and it only takes seconds!

New research update! We replicated Anthropic's circuit tracing methods to test if they can recover a known, simple transformer mechanism.