This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Oscar Obeso
Math undergrad at ETH Zurich.
More info: oscarbalcells.com
Posts
Sorted by New
228
Refusal in LLMs is mediated by a single direction
Ω
7mo
Ω
93
81
Refusal mechanisms: initial experiments with Llama-2-7b-chat
Ω
1y
Ω
7
Wiki Contributions
Comments
Sorted by
Newest