REVIEW 8 cited by
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of the representations and computations learned by very large neural networks. NNsight is an open-source system that extends PyTorch to introduce deferred remote execution. The National Deep Inference Fabric (NDIF) is a scalable inference service that executes NNsight requests, allowing users to share GPU resources and pretrained models. These technologies are enabled by the Intervention Graph, an architecture developed to decouple experimental design from model runtime. Together, this framework provides transparent and efficient access to the internals of deep neural networks such as very large language models (LLMs) without imposing the cost or complexity of hosting customized models individually. We conduct a quantitative survey of the machine learning literature that reveals a growing gap in the study of the internals of large-scale AI. We demonstrate the design and use of our framework to address this gap by enabling a range of research methods on huge models. Finally, we conduct benchmarks to compare performance with previous approaches. Code, documentation, and tutorials are available at https://nnsight.net/.
Forward citations
Cited by 8 Pith papers
-
Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models
Entropy-based CoT pruning does not beat random selection; apparent math-task gains come from numeric tokens, not entropy.
-
Unboxing Diffusion Models for the Arts: Interactive Model Bending and Practice-Based Explainability
Bending different layers of a diffusion model's UNet produces distinct and fairly consistent visual effects across seeds and prompts, and an interactive ComfyUI tool lets artists explore these effects hands-on.
-
Revealing Hidden Model Behaviors with Task-Specific Self-Reports
SAR detects every implanted hidden behavior across eight Qwen3-14B settings and halves IA’s hallucination rate by aligning self-report activations to a contrastive behavior direction under a coherent-English stabilizing cap.
-
Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models
Backdoor triggers in a family of LLMs activate the same attention heads that encode output language, suggesting triggers co-opt existing language circuits rather than forming new ones.
-
Interpreto: An Explainability Library for Transformers
Interpreto provides a unified, documented Python API for attribution and end-to-end concept-based explanation of HuggingFace classification and generation models.
-
Insights into a radiology-specialised multimodal large language model with sparse autoencoders
Applying Matryoshka sparse autoencoders to a radiology-specialised multimodal LLM reveals a minority of interpretable clinical features, while steering them produces unreliable and often off-target report changes.
-
BlueGlass: A Framework for Composite AI Safety
BlueGlass provides composite AI safety infrastructure; its case studies on object-detection VLMs reveal dataset trade-offs, a decoder-layer phase transition in probe accuracy, and SAE-discovered concepts including spu...
-
eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM
A European, NDIF-compatible cluster for remote LLM interpretability is technically feasible and positively received in a 16-person pilot, though the user-study evidence is thin.
Discussion (0). Sign in to comment.