At the link above, we report some developing work from the Anthropic Interpretability team on Crosscoder Model Diffing, which might be of interest to researchers working actively in this space.
As ever, we'd ask readers to treat these results like those of a colleague sharing some thoughts or preliminary experiments for a few minutes at a lab meeting, rather than a mature paper.
Related content
Measuring tactical intelligence targeting and conventional weapons capabilities of AI models
Anthropic’s Frontier Red Team developed new evaluations to measure AI capabilities in tactical intelligence targeting and conventional weapons development.
Read moreAn alignment assessment of recent cybersecurity incidents
We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.
Read moreFormalizing Fermat's Last Theorem
We are sharing the first complete computer-checked proof of Fermat’s Last Theorem. Claude worked largely autonomously over 11 days to write the proof in the Lean programming language.
Read more