Angular Steering

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

• geometry-based steeringconcept0.840
  Paradigm of finding the right geometry (manifold) for principled control.
• direction-based steeringconcept0.832
  Paradigm of finding the right direction in activation space (e.g., linear steering).
• steering vectorsconcept0.802
  A method for modifying model behavior by adding perturbation vectors to activations, used here to try to reduce eval awareness.
• Dynamic Steeringframework0.795
  Steering variants that adaptively modulate steering strength based on input context or token position, addressing when to steer
• Activation Steeringmethod0.793
  Causal intervention technique: edit NLA explanation, reconstruct via AR, use difference as steering vector to manipulate model behavior.
• Stepwise steeringmethod0.793
  Novel method that applies intervention only when the model begins a new thinking step (at the \n\n delimiter) rather than at every token
• Model Steeringconcept0.784
  Using interventions to guide model generation behavior, e.g., adding sentiment vectors at inference time
• Bidirectional Steeringconcept0.783
  Ability to steer model behavior in two opposite semantic directions on a trait.