do facet-level control vectors learned from one backbone transfer to other LLM architectures?

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

• LLMs hierarchically develop understanding of their input data, progressing from surface-level features in early layers to more abstract concepts in later layersclaim0.751
  Interpretation of the layer-by-layer PCA visualizations showing linear structure emerging in early-middle layers
• LLMs trained only on language data have rich enough knowledge of visual structures that decent visual representations can be trained on images generated solely by querying the LLMfinding0.748
  Sharma et al. result supporting cross-modal alignment: language-only models implicitly encode visual structure
• Connecting the Dots: LLMs Can Infer and Verbalize Latent Structure from Disparate Training Data (Treutlein et al. 2024)concept0.744
  Out-of-context reasoning work directly related to synthetic document fine-tuning experiments
• As LLMs scale, they develop increasingly general abstractions, with large models linearly representing abstract concepts like truth that capture shared properties of diverse inputsclaim0.741
  Interpretive claim connecting scale to abstraction level in LLM representations
• Whether conclusions about latent reflection directions generalize to larger LLMs, different architectures, or broader datasets remains to be verified.question0.738
  Key limitation and open question about experimental scope.
• We hypothesize that a Representation Network (RN) emerges from LLM representations, where each dimension is a node and latent connections exist between nodes or clusters of nodes.hypothesis0.730
  Core methodological hypothesis enabling the application of IIT to LLM representation sequences.
• Agent-based routing that activates only trait-relevant CVs reduces noise compared to injecting all Big Five facet vectors simultaneouslyclaim0.729
  Justification for the trait-activated routing design choice
• Facet-Level Personality Controlconcept0.729
  The idea of controlling personality at the granularity of 30 NEO-PI facets rather than five broad dimensions