How does Llama-3.1-8B reason over cyclic concepts?

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

• We hypothesize that Llama-3.1-8B deploys the same base-10 addition circuitry for cyclic reasoning as it uses for general arithmetic, independent of the concept domainhypothesis0.859
  Predictive hypothesis about domain-generality of the identified mechanism
• Llama-3.1-8B uses base-10 addition rather than modular addition to compute cyclic concept sumsfinding0.830
  The central empirical finding that computation does not mirror the circular representational structure
• Llama-3.1-8B representations for cyclic concepts are circularly structuredfinding0.828
  The representation geometry finding that motivates the question about whether computation mirrors it
• Llama-3.1-8B reuses a single generic addition mechanism across all cyclic tasks independently of concept-specific geometryfinding0.825
  Key mechanistic finding showing task-agnostic reuse of arithmetic circuitry
• Does Llama compute modular addition or base-10 addition for cyclic tasks?question0.796
  The specific computational question the paper resolves empirically
• Llama-3.3-70B exhibits internal consistency-checking mechanisms that operate during inferenceclaim0.783
  Central interpretive claim of the paper supported by causal ablation and activation evidence
• Llama-3.1-8B uses task-agnostic Fourier features with periods 2, 5, and 10 (base-10) rather than concept-specific periods (e.g., 12 for months)finding0.772
  The specific Fourier feature periods identified confirm base-10 rather than modular computation
• Steering Llama-3.1 8B along the circular representation manifold produces outputs that follow the natural circle of the behavior manifold, cleanly shifting probability mass from Monday through successive days.finding0.766
  Core empirical result demonstrating that manifold steering produces on-target, behavior-aligned outputs.