←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: 0.22s | source
Show context
gdiamos ◴[22 May 24 08:07 UTC] No.40438502[source]▶
It looks like Anthropic is now leading the charge on safety
replies(1): >>40456745 #
1. maherbeg ◴[23 May 24 16:30 UTC] No.40456745[source]▶
They always were given that is a part of their mission.