© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76249
    Prev
    Next
    INDEX
    Explanations

    items related to tools and equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     addCriterion
    -0.08
     Getter
    -0.07
    enor
    -0.07
    abouts
    -0.07
    478
    -0.07
    за
    -0.07
     ëį¤íĶĦ
    -0.07
    oins
    -0.07
    æķµ
    -0.07
    ASHBOARD
    -0.06
    POSITIVE LOGITS
     wield
    0.10
     usage
    0.08
     Usage
    0.07
    -shaped
    0.07
    -tip
    0.07
    Usage
    0.07
     handle
    0.07
    -handle
    0.06
     holders
    0.06
    blade
    0.06
    Activations Density 0.057%

    No Known Activations