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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88505
    Prev
    Next
    INDEX
    Explanations

    names of directors and actors in film contexts

    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
    fak
    -0.07
    upo
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.06
    ÑģÑıÑĤ
    -0.06
     Ded
    -0.06
    rowned
    -0.06
    uyá»ĩt
    -0.06
     пÑĢодаж
    -0.06
    nte
    -0.06
    ASI
    -0.06
    POSITIVE LOGITS
    çĽ£çĿ£
    0.10
     director
    0.09
     ê°IJëıħ
    0.08
     feature
    0.07
     directors
    0.07
     direction
    0.07
     Director
    0.07
     directing
    0.07
    director
    0.06
     rež
    0.06
    Activations Density 0.028%

    No Known Activations