The paper investigates how semantic meaning is arranged locally within large language models. By using two controlled probes—one cross‑lingual and one refinement probe—on four decoder‑only LLMs, it finds that after removing dominant variance directions, sentence pairs rank by semantic relatedness, semantic factors cluster around an invariant core with structured variation, refinement tightens neighborhoods, and sentence‑level versus token‑local readouts reveal complementary geometric patterns. These results suggest that LLM semantics form local anisotropic neighborhoods that contract when meaning is refined.
By Andr\'es Daniel Godoy Ortiz
The paper compares latent representations in Selective State Space Models (SSMs) like Mamba and Transformers such as Pythia using Sparse Autoencoders. Across a 10‑million token corpus, 99.98% of Mamba features align closely with Pythia’s, supporting the Universality Hypothesis that core semantic representations are similar across architectures. A tiny 0.02% of features diverge, with Mamba’s recurrent bottleneck causing it to compress syntactic anomalies into polysemantic neurons, whereas Pythia’s attention can isolate distinct formatting edge‑cases.
By Rithin Nagaraj, Rupa Laalasa Oruganti, Prerna Subhashchandra Kunder, Ashwini M Joshi
arXiv:2606. 08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features.
By Evan Duan
arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.
By Ayushi Agarwal
The study investigates how post‑training quantization (PTQ) affects proactive interference (PI) in large language models. Using bitsandbytes, the authors compare FP16, INT8, and INT4/NF4 precision across three instruction‑tuned models and find that INT4 quantization markedly degrades accuracy under high interference, with INT8 also incurring a smaller penalty in two of the three models. The degradation is linked to increased same‑key intrusion errors and originates in the quantized transformer backbone rather than the output layer.
By Shayan Shahrabi-Farahani (Shahid Beheshti University, Tehran, Iran), Dara Rahmati (Shahid Beheshti University, Tehran, Iran)
arXiv:2605. 28854v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit remarkable flexibility in adapting to novel tasks from in-context examples without parameter updates, a capability known as in-context learning (ICL).
By Hua-Dong Xiong, Li Ji-An, Robert C. Wilson, Kwonjoon Lee, Xue-Xin Wei
The paper extends mechanistic interpretability of large language models by modeling concepts as low‑dimensional non‑linear manifolds rather than linear subspaces. It introduces a concept‑based alignment (CBA) score to compare these manifolds across layers and models, revealing block structures in intermediate layers, a shift from syntax‑dominated to mixed syntactic‑semantic concepts, and training‑dependent multilingual sharing. The study also shows that alignment patterns differ across model families and training stages, with adjacent stages aligning more closely than distant ones.
By Tido Specht, Elias Benedict Krey, Nils Neukirch, Nils Strodthoff
arXiv:2609.07876v1 Announce Type: cross
Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linea...
By Arjun Patrawala, Jiahai Feng, Erik Jones, Jacob Steinhardt
arXiv:2510.01030v2 Announce Type: replace
Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...
By Zach Studdiford, Timothy T. Rogers, Kushin Mukherjee, Siddharth Suresh
The study investigates whether pretrained transformer models encode functional words—such as pronouns and adverbs—in a way that mirrors human usage. By comparing embeddings of nouns with those of their functional counterparts in both isolated and parallel sentences, the authors find that functional words occupy a central yet distinct position in embedding space and that parallel lexicalized and functional sentences reside in different subspaces. Experiments show that only a mixed training set of functional and lexicalized sentences reveals shared syntactic and semantic structure, whereas training on either type alone fails to capture this parallelism.
By Giuseppe Samo, Vivi Nastase, Paola Merlo
arXiv:2610.29843v1 Announce Type: new
Abstract: Large language models are typically trained with next-token prediction (NTP), which rewards predicting specific tokens rather than explicitly accountin...
By Laya Iyer, Chen Shani
arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
By Partha Pratim Saha, Samarth Raina, Mayur Parvatikar, Amit Dhanda, Vinija Jain, Aman Chadha, Amitava Das