© 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. 128499
    Prev
    Next
    INDEX
    Explanations

    terms related to terms of service and legal disclaimers

    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
    kea
    -0.08
    иÑĤов
    -0.07
    elho
    -0.07
    /meta
    -0.07
    .setAction
    -0.07
    âĢ¦)↵↵
    -0.07
    ç½²
    -0.07
    uteur
    -0.06
    ira
    -0.06
    lien
    -0.06
    POSITIVE LOGITS
    avel
    0.07
    ÏĢο
    0.07
     Finder
    0.06
    amon
    0.06
    ycz
    0.06
    vat
    0.06
    Finder
    0.06
    adera
    0.06
     rip
    0.06
    æ²
    0.06
    Activations Density 0.000%

    No Known Activations