Reusable Feature Atlases Let You Audit New LMs Without Retraining
The authors train a sparse feature atlas on a panel of five 7‑9B instruction‑tuned models, then audit new language models by attaching a simple linear decoder. The atlas provides a stable coordinate system while a residual channel flags features the atlas misses, enabling precise control of injected mechanisms and uncovering framing clusters in targets like Mistral and Qwen‑2.5.