Nnsight Remote Interpretability
This lets you write PyTorch interpretability code once and run it either locally on small models or remotely on massive ones like Llama 3.1 405B through NDIF. The toggle is literally just a `remote=True` flag, which is genuinely useful if you're prototyping interventions on GPT-2 and want to scale up without rewriting everything. It's from the ndif-team with 730+ stars and an ICLR 2025 paper backing it. The main appeal is transparent access to activations and internals across model sizes. If you're doing mechanistic interpretability work and hitting memory walls, this is worth trying.
- skills.sh installs
- 275
- GitHub stars
- 33.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add davila7/claude-code-templates --skill nnsight-remote-interpretability --agent claude-codeInstalls into .claude/skills of the current project.
Files
This lets you write PyTorch interpretability code once and run it either locally on small models or remotely on massive ones like Llama 3.1 405B through NDIF. The toggle is literally just a `remote=True` flag, which is genuinely useful if you're prototyping interventions on GPT-2 and want to scale up without rewriting everything. It's from the ndif-team with 730+ stars and an ICLR 2025 paper backing it. The main appeal is transparent access to activations and internals across model sizes. If you're doing mechanistic interpretability work and hitting memory walls, this is worth trying.
Browse the repository on GitHubSponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/davila7/claude-code-templates
- Categories
- Code Review & Quality, Data Science & ML
- First seen
- Jun 3, 2026
More from davila7/claude-code-templates
All 618- Pytdc275
- Railway Domain275
- Firecrawl Scraper274
- Simpo Training273
- Gene Database272
- Uniprot Database269
- File Uploads268
- Simpy265
- Meme Factory264
- Metabolomics Workbench Database264
- Slack Gif Creator264
- Concise Planning263
- Diffdock262
- Clinpgx Database261
- Tavily Web260
- Gget259
- Crafting Effective Readmes258
- Geo Fundamentals258
- String Database255
- Clinvar Database254
- Shopify Apps254
- Reactome Database252
- Session Handoff251
- Core Components249
Recommended
More Code Review & Quality
12-principles-of-animationraphaelsalaja/userinterface-wikiAudit animation code against Disney's 12 principles adapted for web. Use when reviewing motion, implementing animations, or checking animation quality. Outputs 275skills.sh installs
brand-agencyglebis/claude-skillsApplies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces. This skill should be used when bra274skills.sh installs
fal-upscalefal-ai-community/skillsUpscale and enhance image resolution using AI. Use when the user requests "Upscale image", "Enhance resolution", "Make image bigger", "Increase quality", or sim273skills.sh installs
alicloud-ai-video-wan-r2vcinience/alicloud-skillsGenerate reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos from referenc272skills.sh installs
data-visualizationlangchain-ai/deepagentsUse for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts,272skills.sh installs
evaluation-harnesspatricio0312rev/skillsBuilds repeatable evaluation systems with golden datasets, scoring rubrics, pass/fail thresholds, and regression reports. Use for "LLM evaluation", "testing AI 272skills.sh installs