Preventative Steering During Training

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• steering (intervention on internals)concept0.796
  General technique of modifying activations to control model behavior.
• direction-based steeringconcept0.777
  Paradigm of finding the right direction in activation space (e.g., linear steering).
• Bidirectional Steeringconcept0.773
  Ability to steer model behavior in two opposite semantic directions on a trait.
• steering vectorsconcept0.761
  A method for modifying model behavior by adding perturbation vectors to activations, used here to try to reduce eval awareness.
• Stepwise steeringmethod0.758
  Novel method that applies intervention only when the model begins a new thinking step (at the \n\n delimiter) rather than at every token
• Activation Steeringmethod0.757
  Causal intervention technique: edit NLA explanation, reconstruct via AR, use difference as steering vector to manipulate model behavior.
• geometry-based steeringconcept0.755
  Paradigm of finding the right geometry (manifold) for principled control.
• Contrastive Activation Steeringmethod0.751
  Core technique: takes mean difference of model activations on contrastive prompts and adds the resulting vector to the residual stream at inference time.