Pith. sign in

REVIEW 5 cited by

Language Models Use Trigonometry to Do Addition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.00873 v1 pith:HMGHJP35 submitted 2025-02-02 cs.AI cs.CLcs.LG

classification cs.AIcs.CLcs.LG
keywords additionhelixllmsmathematicalmodelcausallycomputeeven
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Mathematical reasoning is an increasingly important indicator of large language model (LLM) capabilities, yet we lack understanding of how LLMs process even simple mathematical tasks. To address this, we reverse engineer how three mid-sized LLMs compute addition. We first discover that numbers are represented in these LLMs as a generalized helix, which is strongly causally implicated for the tasks of addition and subtraction, and is also causally relevant for integer division, multiplication, and modular arithmetic. We then propose that LLMs compute addition by manipulating this generalized helix using the "Clock" algorithm: to solve $a+b$, the helices for $a$ and $b$ are manipulated to produce the $a+b$ answer helix which is then read out to model logits. We model influential MLP outputs, attention head outputs, and even individual neuron preactivations with these helices and verify our understanding with causal interventions. By demonstrating that LLMs represent numbers on a helix and manipulate this helix to perform addition, we present the first representation-level explanation of an LLM's mathematical capability.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Temporal Preference Concepts and their Functions in a Large Language Model

    cs.LG 2026-05 unverdicted novelty 6.5 of 10

    Temporal preference in Qwen3-4B-Instruct-2507 localizes to layers 17–35 (especially L24 attention), has curved residual-stream geometry, is behaviorally unstable, and can be bidirectionally steered.

  2. Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Llama-3 arithmetic is computed by a shared neuron set across symbolic, text, and code formats, and cross-format failures are activation-state differences, not distinct circuits.

  3. Singular Vectors of Attention Heads Align with Features

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Under linear feature representations, attention-head singular vectors align with attended features under near-isotropy, and this predicts sparse attention decomposition seen in Pythia and GPT-2.

  4. Modular Arithmetic: Language Models Solve Math Digit by Digit

    cs.CL 2025-08 conditional novelty 6.0 of 10

    LLMs perform 3-digit addition and subtraction via digit-position-specific MLP circuits that can be intervened upon to change individual output digits.

  5. Prompting as Scientific Inquiry

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Position paper arguing that prompting LLMs is a form of behavioral science and should be recognized as a core scientific method alongside mechanistic interpretability.

Pith tools