knowingly-wrong
/

persona-vectors

persona-vectors

steering-vectors

activation-steering

interpretability

Model card Files Files and versions

persona-vectors

Commit History

Nov 4 Yesterday

17:59
Link paper (arXiv:2611.05287)

mollejasaurio

Verified signature
46a6bed

Sep 30

14:11
Update README.md

suroRitch

Verified signature
c2f68b4
14:09
Add persona directions for Qwen3.6-27B and Qwen2.5-7B

suroRitch

Verified signature
286be0a
14:09
initial commit

suroRitch

Verified signature
e3da501