arXiv AI
Signatures of semantic search in the activations of large language models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 21
Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models
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.
arXiv AI
Jun 9
Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
arXiv Machine Learning
Jun 16
Emergent retokenization symmetry in large language models: phenomenology and applications
arXiv:2606. 15521v1 Announce Type: cross Abstract: Tokenization introduces representational redundancy: under a fixed token vocabulary, every byte string admits many valid token encodings, or segmentations, that decode to the same surface string.
arXiv AI
Jul 10
Agentic Neural Architecture Search
arXiv:2607. 07984v1 Announce Type: new Abstract: Neural architecture search (NAS) methods have grown increasingly efficient, yet they remain bounded by manually engineered search spaces that require substantial domain expertise and must be rebuilt for every new task.
arXiv Machine Learning
Sep 21
Exemplar Partitioning for Mechanistic Interpretability
The paper introduces Exemplar Partitioning (EP), an unsupervised technique that constructs interpretable feature dictionaries from large language model activations by clustering streamed activations into Voronoi regions defined by exemplars and their averages. EP allows comparison of dictionaries across layers, checkpoints, and architectures, and demonstrates utility in interpreting model behavior, tracking training dynamics, detecting hidden concepts, and enabling targeted interventions. Experiments on Gemma‑2‑2B and Llama‑3.1‑8B show EP can reveal how instruction tuning reorganizes harmful prompt activations, facilitate interventions that alter model responses, and achieve high concept‑detection performance while requiring far fewer construction tokens than comparable methods.
arXiv Machine Learning
Sep 2
Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training
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...