Agentic behavior in LLMs

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

• Behavioral organization of LLMsconcept0.802
  The layered structure of which behaviors a model defaults to, can be steered toward, or resists—the central object of study
• Emotion Features in LLMsconcept0.771
  Internal representations encoding emotion concepts in large language models, identified by probing and SAE methods
• Understanding how LMs learn linguistic behaviours may offer insights into fundamental properties of languagehypothesis0.768
  Forward-looking hypothesis linking LM mechanism analysis to linguistic theory
• Where does reliable, goal-directed behavior come from in LLMs if it is not explicitly programmed?question0.767
  Opening motivating question that UCCT attempts to answer through semantic anchoring
• Refusal Direction in LLMsconcept0.765
  Prior finding that LLM refusal is mediated by a single latent direction, analogous to this paper's reflection direction.
• Persona Assignment to LLMsconcept0.759
  The practice of providing LLMs with a persona description to shape their generated responses
• LLM Meta-Cognitionconcept0.758
  The ability of LLMs to monitor and evaluate their own reasoning, closely related to reflection.
• Truthful behavior in LLMs is not confined to a single linear axis; multiple orthogonal directions can independently mediate itclaim0.757
  Central interpretive claim of the paper