Cole Blondin

Dharunish Yugeswardeenoo, Harshil Nukala, Ved Shah et al.

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities but continue to struggle with arithmetic tasks. Prior works largely focus on outputs or prompting strategies, leaving the open question of the internal structure through which models do arithmetic computation. In this work, we investigate whether LLMs encode operator precedence in their internal representations via the open-source instruction-tuned LLaMA 3.2-3B model. We constructed a dataset of arithmetic expressions with three operands and two operators, varying the order and placement of parentheses. Using this dataset, we trace whether intermediate results appear in the residual stream of the instruction-tuned LLaMA 3.2-3B model. We apply interpretability techniques such as logit lens, linear classification probes, and UMAP geometric visualization. Our results show that intermediate computations are present in the residual stream, particularly after MLP blocks. We also find that the model linearly encodes precedence in each operator's embeddings post attention layer. We introduce partial embedding swap, a technique that modifies operator precedence by exchanging high-impact embedding dimensions between operators.

Cheng-Ting Chou, George Liu, Jessica Sun et al.

Deterministically controlling the target generation language of large multilingual language models (LLMs) remains a fundamental challenge, particularly in zero-shot settings where neither explicit language prompts nor fine-tuning are available. In this work, we investigate whether sparse autoencoder (SAE) features, previously shown to correlate with interpretable model behaviors, can be leveraged to steer the generated language of LLMs during inference. Leveraging pretrained SAEs on the residual streams of Gemma-2B and Gemma-9B, we identify features whose activations differ most significantly between English and four target languages: Chinese, Japanese, Spanish, and French. By modifying just a single SAE feature at one transformer layer, we achieve controlled language shifts with up to 90\% success, as measured by FastText language classification, while preserving semantic fidelity according to LaBSE (Language-Agnostic BERT Sentence Embedding) similarity. Our analysis reveals that language steering is most effective in mid-to-late transformer layers and is amplified by specific attention heads disproportionately associated with language-sensitive SAE features. These results demonstrate the promise of sparse feature steering as a lightweight and interpretable mechanism for controllable multilingual generation.

Stanley Yu, Vaidehi Bulusu, Oscar Yasunaga et al.

Large Language Models (LLMs) exhibit strong conversational abilities but often generate falsehoods. Prior work suggests that the truthfulness of simple propositions can be represented as a single linear direction in a model's internal activations, but this may not fully capture its underlying geometry. In this work, we extend the concept cone framework, recently introduced for modeling refusal, to the domain of truth. We identify multi-dimensional cones that causally mediate truth-related behavior across multiple LLM families. Our results are supported by three lines of evidence: (i) causal interventions reliably flip model responses to factual statements, (ii) learned cones generalize across model architectures, and (iii) cone-based interventions preserve unrelated model behavior. These findings reveal the richer, multidirectional structure governing simple true/false propositions in LLMs and highlight concept cones as a promising tool for probing abstract behaviors.

Advey Nandan, Cheng-Ting Chou, Amrit Kurakula et al.

We investigate the phenomenon of neuron universality in independently trained GPT-2 Small models, examining these universal neurons-neurons with consistently correlated activations across models-emerge and evolve throughout training. By analyzing five GPT-2 models at five checkpoints, we identify universal neurons through pairwise correlation analysis of activations over a dataset of 5 million tokens. Ablation experiments reveal significant functional impacts of universal neurons on model predictions, measured via cross entropy loss. Additionally, we quantify neuron persistence, demonstrating high stability of universal neurons across training checkpoints, particularly in early and deeper layers. These findings suggest stable and universal representational structures emerge during language model training.

Daniel Son, Sanjana Rathore, Andrew Rufail et al.

We investigate feature universality in Gemma-2 language models (Gemma-2-2B and Gemma-2-9B), asking whether models with a four-fold difference in scale still converge on comparable internal concepts. Using the Sparse Autoencoder (SAE) dictionary-learning pipeline, we utilize SAEs on each model's residual-stream activations, align the resulting monosemantic features via activation correlation, and compare the matched feature spaces with SVCCA and RSA. Middle layers yield the strongest overlap, while early and late layers show far less similarity. Preliminary experiments extend the analysis from single tokens to multi-token subspaces, showing that semantically similar subspaces interact similarly with language models. These results strengthen the case that large language models carve the world into broadly similar, interpretable features despite size differences, reinforcing universality as a foundation for cross-model interpretability.