Cover Image

Probing for Representation Manifolds in Superposition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Modell, Alexander
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence 68T07 I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Origins of Representation Manifolds in Large Language Models
by: Modell, Alexander, et al.
Published: (2025)

Geometric Evolution Maps: Extracting Stable Concept Probes from Transformer Residual Streams
by: Henry, James
Published: (2026)

A Practical Guide to Streaming Continual Learning
by: Cossu, Andrea, et al.
Published: (2026)

ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference
by: Das, Sourav
Published: (2026)

ProactBench: Beyond What The User Asked For
by: Harfi, Sepehr, et al.
Published: (2026)

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure
by: Sarkar, Nilesh, et al.
Published: (2026)

How Pruning Reshapes Features: Sparse Autoencoder Analysis of Weight-Pruned Language Models
by: Borobia, Hector, et al.
Published: (2026)

The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
by: Henry, James
Published: (2026)

Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence
by: Giannini, Federico, et al.
Published: (2026)

cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series
by: Giannini, Federico, et al.
Published: (2026)

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters
by: Mutlu, Abdulvahap, et al.
Published: (2026)

DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
by: Wang, Ziyi, et al.
Published: (2026)

CWM: An Open-Weights LLM for Research on Code Generation with World Models
by: FAIR CodeGen team, et al.
Published: (2025)

Stick to your Role! Stability of Personal Values Expressed in Large Language Models
by: Kovač, Grgur, et al.
Published: (2024)

Data-driven Circuit Discovery for Interpretability of Language Models
by: Rai, Daking, et al.
Published: (2026)

Extending $μ$P: Spectral Conditions for Feature Learning Across Optimizers
by: Gupta, Akshita, et al.
Published: (2026)

DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas
by: Wang, Zhen, et al.
Published: (2025)

Scalify: scale propagation for efficient low-precision LLM training
by: Balança, Paul, et al.
Published: (2024)

When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models
by: Basu, Abhinaba
Published: (2026)

FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA
by: Zhang, Haoran, et al.
Published: (2026)

Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts
by: Garg, Saloni, et al.
Published: (2026)

Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
by: Jeong, Kyungwon, et al.
Published: (2026)

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
by: Nauen, Tobias Christian, et al.
Published: (2024)

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models
by: Guo, Dongxin, et al.
Published: (2026)

Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments
by: Giannini, Federico, et al.
Published: (2026)

Stealth edits to large language models
by: Sutton, Oliver J., et al.
Published: (2024)

NeuronSpark: A Spiking Neural Network Language Model with Selective State Space Dynamics
by: Tang, Zhengzheng
Published: (2026)

TowerVision: Understanding and Improving Multilinguality in Vision-Language Models
by: Viveiros, André G., et al.
Published: (2025)

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
by: Chen, Yihong, et al.
Published: (2022)

MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
by: Wang, Yihao, et al.
Published: (2026)

The Curious Case of In-Training Compression of State Space Models
by: Chahine, Makram, et al.
Published: (2025)

Harnessing non-adversarial robustness in large language models
by: Zhou, Qinghua, et al.
Published: (2026)

GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping
by: Wen, Qifu, et al.
Published: (2025)

MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence
by: Giannini, Federico, et al.
Published: (2026)

CLMN: Concept based Language Models via Neural Symbolic Reasoning
by: Yang, Yibo
Published: (2025)

Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds
by: Alpay, Faruk, et al.
Published: (2026)

Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible
by: Zhao, Lepeng, et al.
Published: (2026)

ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
by: Danieli, Federico, et al.
Published: (2025)

Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning
by: Thil, Lucas-Andreï, et al.
Published: (2024)

Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization
by: Bronec, Jan, et al.
Published: (2025)