This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
neverix
Posts
Sorted by New
5
Evolutionary prompt optimization for SAE feature visualization
17h
0
12
SAE features for refusal and sycophancy steering vectors
1mo
0
17
Extracting SAE task features for in-context learning
3mo
0
25
Self-explaining SAE features
3mo
0
Wiki Contributions
Comments
Sorted by
Newest
Power-seeking can be probable and predictive for trained agents
neverix
2y
0
0
A0>A1
How is orbit comparison for sets defined?
[This comment is no longer endorsed by its author]
Reply
How is orbit comparison for sets defined?