The paper investigates how LLaMA 3.1‑8B models numerical sequence patterns, focusing on time‑series prediction. By designing a task that requires detecting structural cues—specifically first differences in a sequence—the authors show that the model performs well and internally computes and stores these differences. Probing and activation‑patching experiments reveal that LLaMA retrieves and applies the first‑difference via an induction‑like circuit, marking one of the first demonstrations of concept induction in large language models.
arXiv:2508. 12448v2 Announce Type: replace-cross Abstract: In-context learning (ICL) lets large language models (LLMs) solve new tasks from prompts alone, across an ever-widening range of domains, yet the mechanisms underlying this ability remain poorly understood.
arXiv:2607. 12279v1 Announce Type: cross Abstract: Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an ASCII table.
The paper introduces adVersarial Parameter Decomposition (VPD), a method that splits a language model’s parameters into simple subcomponents, each responsible for a small part of the model’s algorithm. VPD optimizes these decompositions so that the model’s input‑output behavior remains intact even when many subcomponents are removed, including adversarially chosen ones. This approach enables a new form of circuit analysis by tracing how sequences of parameter subcomponents interact to produce outputs for specific inputs.
arXiv:2608. 25897v1 Announce Type: new Abstract: Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior.
arXiv:2601. 21996v2 Announce Type: replace-cross Abstract: While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive.
Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an ASCII table. These are all tasks that language models can do that requires tracking how many tokens remain before a target.
Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods...
The paper argues that pattern recognition and step‑by‑step reasoning lie on a spectrum, with large language models (LLMs) learning the latter when the next token depends on only a few preceding tokens. It formalises reasoning traces as paths on a De Bruijn graph, showing that the number of edges is far smaller than the number of possible traces, making step‑by‑step reasoning sample‑efficient. Experiments fine‑tuning Qwen2.5‑1.5B‑Instruct demonstrate that a moderate density of states balances accuracy and robustness, and that real‑world models like Qwen3 retain most of their performance even when attention is limited to a small sliding window.
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv:2608.29034v1 Announce Type: cross Abstract: A wide range of methods have been proposed for interpreting language models, delivering important insights into their inner workings. However, differ...
arXiv:2606. 11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs.
arXiv:2512. 03578v3 Announce Type: replace-cross Abstract: Time series extrinsic regression (TSER) refers to the task of predicting a continuous target variable from an input time series.