© 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. 71285
    Prev
    Next
    INDEX
    Explanations

    instances of actors or characters being referred to or described in movies or shows

    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
    pte
    -0.07
    .rd
    -0.07
    otre
    -0.07
    etur
    -0.06
     é«
    -0.06
    agal
    -0.06
    amework
    -0.06
    ponge
    -0.06
    xon
    -0.06
    ete
    -0.06
    POSITIVE LOGITS
    iten
    0.07
    alsy
    0.07
    387
    0.06
     incre
    0.06
    204
    0.06
     incr
    0.06
    ITH
    0.06
    elligence
    0.06
    UDA
    0.06
    arded
    0.06
    Activations Density 0.002%

    No Known Activations