x

LESSWRONG

LW

ewern — LessWrong

ewern

ewern

Message

https://www.x.com/ericwerner_

9

1

3y

ewern

https://www.x.com/ericwerner_

I used this repo to partially replicate Anthropic's Emotion Concepts paper in a day

tl;dr This post introduces the traitinterp repo I used to partially replicate Anthropic's Emotion Concepts paper on Llama 3.3 70B Instruct. github.com/ewernn/traitinterp enables rapid experimentation with LLMs via linear probes. Emotion Concepts replication write-up is available --> here <-- replication guide here Figure 0: Screenshot from replication write-up (btw, the...