© 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 EvalsExportsinterp-engineNEWAPI 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. 54324
    Prev
    Next
    INDEX
    Explanations

    specific references to divine intervention or biblical passages

    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
    ampo
    -0.07
     numer
    -0.07
    umbo
    -0.06
    _marshall
    -0.06
    igue
    -0.06
    icias
    -0.06
    ená
    -0.06
     Rub
    -0.06
    akash
    -0.06
    idunt
    -0.06
    POSITIVE LOGITS
     Brace
    0.08
     Moff
    0.07
    BJ
    0.07
    riors
    0.07
    hap
    0.07
    Ł
    0.07
    .depth
    0.06
    bj
    0.06
    uds
    0.06
     squared
    0.06
    Activations Density 0.002%

    No Known Activations