hypothesis

active

hypothesis: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-domain

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 domain

Predictive hypothesis about domain-generality of the identified mechanism

Source paper

extracted_from

Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts

(2026) · Sheridan Feucht · Tal Haklay · Usha Bhalla · Daniel Wurgaft +8

Neighborhood — ranked by edge-count

Findings (1)

finding

Llama-3.1-8B reuses a single generic addition mechanism across all cyclic tasks independently of concept-specific geometry
associated_with
Key mechanistic finding showing task-agnostic reuse of arithmetic circuitry

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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 sumsfinding0.902
The central empirical finding that computation does not mirror the circular representational structure
Does Llama compute modular addition or base-10 addition for cyclic tasks?question0.868
The specific computational question the paper resolves empirically
How does Llama-3.1-8B reason over cyclic concepts?question0.859
The empirical question the paper addresses through mechanistic investigation
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)finding0.841
The complete mechanistic algorithm discovered for cyclic concept reasoning
An addition module in layer 18 of Llama-3.1 8B performs arithmetic using circular geometric representations of numbers.quote0.828
Verbatim summary of the main discovery.
Llama-3.3-70B exhibits internal consistency-checking mechanisms that operate during inferenceclaim0.819
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)finding0.808
The specific Fourier feature periods identified confirm base-10 rather than modular computation
Base-10 Addition Mechanism in Llamaconcept0.807