#steering

3 pages search “steering” ↳ all tags

Wiki 3

  • Abliteration Removing an LLM's refusal behavior by identifying and suppressing the refusal direction in activation space
  • Steering Is Interesting Again (Goedecke) Goedecke's case that steering vectors are worth a second look now that local frontier models exist, with antirez's DwarfStar 4 as evidence
  • Steering Vectors Manipulating LLM activations mid-inference to bias output toward a concept, without changing the weights