© 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. 73880
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assistance or problem-solving

    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
     +
    -0.06
    бо
    -0.06
     —
    -0.06
    996
    -0.06
     cylinders
    -0.06
     (*
    -0.05
     Susp
    -0.05
     discriminate
    -0.05
     Tanks
    -0.05
     -
    -0.05
    POSITIVE LOGITS
    ocaust
    0.08
    ÑĪÑĤов
    0.08
     ÑĢаб
    0.07
    fbe
    0.07
    crets
    0.07
    LOPT
    0.07
    à¥ĩण
    0.07
    .Cond
    0.07
    ayo
    0.07
    esan
    0.07
    Activations Density 0.000%

    No Known Activations