1/6: Can we use an LLM’s hidden activations to predict and prevent wrong predictions? When it comes to arithmetic, yes! I’m presenting new work w/ @alestolfo.bsky.social “Probing for Arithmetic Errors in LMs” @ #ICML2025 Act Interp WS 🧵 below

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!

Our paper "Improving Instruction-Following in Language Models through Activation Steering” has been accepted to #ICLR2025! We're also excited to share that our public GitHub repo is now live. Code: github.com/microsoft/ll... Camera-ready: arxiv.org/abs/2410.12877