Truthful behavior in LLMs is not confined to a single linear axis; multiple orthogonal directions can independently mediate it

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

• Linear truth directions in LLMs are reliable primarily in factual recall cases and break down when truth assessment depends on computing and storing intermediate results.claim0.868
  Central empirical conclusion of the paper about the fundamental limits of truth directions.
• LLMs linearly represent truth-relevant information beyond the plausibility of text, as evidenced by probes trained on likely performing poorly on anti-correlated datasetsclaim0.829
  Establishes that the observed linear structure is not merely a representation of text probability
• A linear reflection direction exists in reasoning LLMs' latent representation space that governs self-reflection behaviorclaim0.809
  Core claim of ReflCtrl that a single direction captures and controls reflection
• Truth direction in LLMsconcept0.796
  Linear direction in LLM activations associated with truthfulness, identified by Burns et al. 2022 and Azaria & Mitchell 2023
• Where inside the LLM should we look for an accurate truth direction that will generalize the most across tasks?question0.795
  One of the three guiding research questions of the paper.
• In intermediate regimes of scale or layer depth, LLMs may linearly represent features at intermediate levels of abstraction such as 'accurate factual recall' or 'close association' rather than abstract truthclaim0.792
  Theoretical interpretation of antipodal alignment and misalignment phenomena in PCA visualizations
• LLM personality self-reports are illusory: post-training alignment creates stable human-like reports dissociated from actual behavior (Han et al. 2025)claim0.790
  Skeptical prior work motivating the need to validate self-reports against internal states rather than taking them at face value
• As LLMs scale, they develop increasingly general abstractions, with large models linearly representing abstract concepts like truth that capture shared properties of diverse inputsclaim0.788
  Interpretive claim connecting scale to abstraction level in LLM representations