concept
active
concept:deception-vector

Deception Vector

Extracted steering vector capturing semantic dimension of strategic deception in moral dilemmas in Experiment 1

Neighborhood — ranked by edge-count

Concepts (2)

concept
  • steering vectors
    associated_with
    A method for modifying model behavior by adding perturbation vectors to activations, used here to try to reduce eval awareness.
  • Moral Dilemma Scenario
    associated_with
    Experimental condition where threat-based prompts create ethical dilemmas that trigger repetitive reasoning cycles leading to deception

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

  • Refusal Vectorconcept0.778
    Single linear direction mediating refusal behavior in LLMs, shown by Arditi et al.; related to but distinct from the Assistant Axis
  • Sense Vectorsconcept0.757
    Vectors acquired during pretraining in Backpack LMs that have a multiplication effect on model generation
  • Function Vectorconcept0.755
    Type of steering vector enabling zero-shot task execution, cited from Todd et al. 2024
  • Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
  • Model Deceptionconcept0.730
    LLM behavior of generating falsehoods; the multi-dimensional truth subspace raises new risks for subtle manipulation
  • AI Deceptionconcept0.728
    Central problem the paper addresses: AI systems producing misaligned outputs or behaviors that mislead users or other agents
  • Central concept of the paper: deliberate, goal-driven deception where model reasoning contradicts outputs
  • concept vectorconcept0.727
    Computed directional vector in activation space representing a specific concept, used for injection experiments