method
active
method:fourier-harmonic-decomposition-of-curve-blockFourier harmonic decomposition of curve block
Decomposes block contribution along orientation.
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Higher-order modes.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Rules out artifact reading of higher harmonics.
- The 28 identified neurons can be partitioned into disjoint clusters each computing a different Fourier period sum
- Features identified in Llama-3.1-8B that compute sums using periods respecting base-10 addition (2, 5, 10) rather than concept-specific periods
- Neuroscience analogy.
- Method used to identify the periodic features and their periods in Llama-3.1-8B's MLP neurons
- Framework decomposing network parameters into sum of sparsely used vectors in parameter space.
- Variance-fraction test with θ=2 null baseline for modular addition.