Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44037
    Prev
    Next
    INDEX
    Explanations

    mentions of the "Guardians of the Galaxy" franchise

    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
    hurst
    -0.07
    osti
    -0.07
    veau
    -0.07
    folio
    -0.07
     Sloan
    -0.07
    deo
    -0.06
    ibase
    -0.06
    kker
    -0.06
     Pharm
    -0.06
    amation
    -0.06
    POSITIVE LOGITS
     Galaxy
    0.08
     Know
    0.07
    èĨ
    0.07
     GAL
    0.07
     Ga
    0.07
    Gal
    0.07
     Gal
    0.07
    onor
    0.06
    ì²ł
    0.06
     Marvel
    0.06
    Activations Density 0.004%

    No Known Activations