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)

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

• Llama-3.1-8B uses base-10 addition rather than modular addition to compute cyclic concept sumsfinding0.833
  The central empirical finding that computation does not mirror the circular representational structure
• Llama-3.1-8B implements a two-stage algorithm: (1) compute integer sum via base-10 addition (e.g., six + August = 14), then (2) map sum to cyclic concept space (14 → February)finding0.825
  The complete mechanistic algorithm discovered for cyclic concept reasoning
• 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 domainhypothesis0.808
  Predictive hypothesis about domain-generality of the identified mechanism
• Llama-3.1-8B reuses a single generic addition mechanism across all cyclic tasks independently of concept-specific geometryfinding0.804
  Key mechanistic finding showing task-agnostic reuse of arithmetic circuitry
• Does Llama compute modular addition or base-10 addition for cyclic tasks?question0.802
  The specific computational question the paper resolves empirically
• Factual tasks F0-F3 reach near-perfect AUROC in early-to-mid layers of Llama-3.1-8B; arithmetic tasks A1-A3 emerge much later; counting tasks F4-F5 emerge late similar to arithmetic.finding0.800
  Core empirical finding about layer-dependent truth direction emergence across task types.
• Llama-3.1 8B internal representations for the seven days of the week form seven clusters in a circle in activation space.finding0.791
  Empirical observation establishing that Llama's internal representations for days-of-week have circular geometric structure.
• LLaMA-2-70B displays summarization behavior over punctuation tokens in a context-dependent way: present for cities but not for sp_en_transfinding0.785
  Contrasts with 7B and 13B which show consistent summarization behavior; may complicate localization at 70B scale