Fine‑tuning reshapes internal representations of large language models, affecting attention patterns and layer‑wise activations. The study shows that components identified by EAP as important for task performance cluster in specific layers, yet these layers do not align with those undergoing the largest representational changes. Additionally, overlapping EAP components across different tasks do not guarantee cross‑task transfer and can even degrade performance when tasks differ in nature.
By Lingfang Li, Procheta Sen, Shubham Das, Danushka Bollegala
arXiv:2609.36221v1 Announce Type: new
Abstract: The way a model distributes activity over each layer's attention heads offers a coarse view of how it routes information through depth; how this change...
By Johnny Jingze Li, Abdulla Kuleib, Kalyan Basu, Gabriel A. Silva
The study investigates the consistency and specificity of language model circuits across six tasks and five models, focusing on component-level (attention heads and MLP blocks) and neuron-level circuits. Component-level circuits are highly consistent and causally important but lack task specificity, as ablating a circuit for one task similarly harms performance on other tasks. Neuron-level circuits show higher task specificity but lower consistency, with overlap mainly between closely related tasks. The analysis of Llama‑3.2‑3B reveals that shared components are predominantly MLP blocks, while attention heads act as generic attention‑sink heads.
By Michael Li, Nishant Subramani
The paper presents a mean‑field analysis of attention in language models, defining an average attention kernel that propagates representations layer by layer. When conditioned on a whole corpus, the kernel predicts the average evolution of representation geometry; when conditioned on a single context, it predicts the expected geometry for that context. The difference between actual attention and the mean‑field prediction—called the mean‑field deviation—captures context‑specific computation, revealing how models diverge from average behavior during training and in few‑shot tasks.
By Micah Adler, John W. Byers, Mark Crovella
arXiv:2610.20179v1 Announce Type: cross
Abstract: Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot...
By Davide Baldelli, Robyn Kozierok, Mirko Bronzi, Damiano Fornasiere
arXiv:2608. 11510v1 Announce Type: cross Abstract: Congruency effects, observed in conflict tasks such as Stroop and flanker tasks, have been investigated for nearly a century in psychology and neuroscience, but their mechanistic basis is not fully understood.
By Xiaoyang Hu, Mike Angstadt, Shane Storks, Zan Huang, Aman Taxali, Alex Weigard, Richard L. Lewis, Chandra Sripada
Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot control what their activations encode. Humans can l...
arXiv:2604. 09670v2 Announce Type: replace-cross Abstract: Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals.
By Hua-Dong Xiong, Li Ji-An, Jiaqi Huang, Robert C. Wilson, Kwonjoon Lee, Xue-Xin Wei
The paper introduces Declarative Attention (DA), a protocol that lets language models explicitly declare which parts of their context to focus on during generation. By partitioning decoding into full-context, region-specific, and recent-output-only modes, the inference engine can skip large portions of the KV cache, dramatically reducing attended tokens. Experiments on 15 long-context tasks with off-the-shelf models show significant savings (52.0% and 31.1% reductions) with only modest accuracy drops that diminish as model size increases.
By Namgyu Ho, Huzama Ahmad, Woosung Koh, Se-Young Yun, Tal Schuster, Cicero Nogueira dos Santos
arXiv:2609.01170v1 Announce Type: new
Abstract: Large language models exhibit a modular internal organization that mirrors well-studied functional networks of the human brain, but how this organizati...
By Guangqi Li, Yongxin Li
arXiv:2606. 05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families.
By Yongzhong Xu
arXiv:2609.35599v2 Announce Type: replace
Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise thei...
By Luke Leckie, Peter M. Todd, Jacob G. Foster