© 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. 117131
    Prev
    Next
    INDEX
    Explanations

    punctuation and expressions of enthusiasm

    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
     also
    -0.07
     Bot
    -0.07
     bot
    -0.06
    Bot
    -0.06
    ault
    -0.06
    uhl
    -0.06
    mania
    -0.06
    dea
    -0.06
    yk
    -0.06
    bots
    -0.06
    POSITIVE LOGITS
    UsageId
    0.07
    IIIK
    0.07
    HeaderCode
    0.07
    _ctrl
    0.07
    refs
    0.06
    WithTag
    0.06
    actionDate
    0.06
    .Magenta
    0.06
    standen
    0.06
    osu
    0.06
    Activations Density 0.023%

    No Known Activations