Fourier features with period 10 contribute to base-10 sum computation in the 28-neuron cluster

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

• The Fourier feature periods (2, 5, 10) respect standard base-10 addition structure rather than cyclic concept periodicityclaim0.846
  Mechanistic claim linking identified Fourier features to base-10 arithmetic
• Disjoint neuron clusters for Fourier periodsconcept0.830
  The 28 identified neurons can be partitioned into disjoint clusters each computing a different Fourier period sum
• The 28 MLP neurons at layer 18 can be partitioned into disjoint clusters each computing the sum for a Fourier feature with a different periodfinding0.781
  Structural finding showing modular organization within the sparse neuron set
• Arabic feature A/1/3450 has 27 neurons with coefficient magnitude ≥0.1 and three largest coefficients are negative; most correlated neuron responds to mixture of non-English languagesfinding0.766
  Demonstrates that the Arabic feature is not aligned to any single neuron
• Features in A/1 have median activation correlation of 0.72 with most similar feature in B/1; neurons have median 0.46finding0.758
  Systematic comparison showing features are substantially more universal than neurons across models
• No neuron found with Hebrew Unicode block in top dataset examples; most correlated neuron A/neurons/489 has correlation of only 0.1finding0.757
  Hebrew feature is effectively invisible in the neuron basis
• Fourier Features for Numerical Computationconcept0.752
• Fourier analysis of neural activationsmethod0.748
  Method used to identify the periodic features and their periods in Llama-3.1-8B's MLP neurons