LESSWRONG
is fundraising!
Tags
LW
$

Activation Engineering

•

Applied to Deep Causal Transcoding: A Framework for Mechanistically Eliciting Latent Behaviors in Language Models by TurnTrout 21d ago

•

Applied to A Sober Look at Steering Vectors for LLMs by Joschka Braun 1mo ago

•

Applied to Avoiding jailbreaks by discouraging their representation in activation space by Guido Bergman 3mo ago

•

Applied to Validating / finding alignment-relevant concepts using neural data by Bogdan Ionut Cirstea 3mo ago

•

Applied to Programming Refusal with Conditional Activation Steering by Bruce W. Lee 3mo ago

•

Applied to Activation Engineering Theories of Impact by kubanetics 5mo ago

•

Applied to I found >800 orthogonal "write code" steering vectors by Jacob G-W 5mo ago

•

Applied to An Introduction to Representation Engineering - an activation-based paradigm for controlling LLMs by Jan Wehner 5mo ago

•

Applied to Control Vectors as Dispositional Traits by Jan Wehner 6mo ago

•

Applied to Representation Tuning by Jan Wehner 6mo ago

•

Applied to LLMs Universally Learn a Feature Representing Token Frequency / Rarity by Sean Osier 6mo ago

•

Applied to Jailbreak steering generalization by Nina Panickssery 6mo ago

•

Applied to Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller by Henry Cai 6mo ago

•

Applied to Introducing SARA: a new activation steering technique by Alejandro Tlaie 7mo ago

•

Applied to Mechanistically Eliciting Latent Behaviors in Language Models by TurnTrout 8mo ago