Anthropic Researchers Map Features in Claude 3 Sonnet
Anthropic Researchers Map Features in Claude 3 Sonnet
transformer-circuits.pub
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Interesting research from Anthropic. I'm looking forward to reading follow-on work, and I really hope that this will be tested on open source models (like Mistral) to confirm the method.