←back to thread

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

(transformer-circuits.pub)
168 points 1wheel | 1 comments | 21 May 24 15:15 UTC | HN request time: 1.041s | source
1. null_point ◴[21 May 24 15:31 UTC] No.40429743[source]▶
Strategic timing for the release of this paper. As of last week OpenAI looks weak in their commitment to _AI Safety_, losing key members of their Super Alignment team.