© 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. 14780
    Prev
    Next
    INDEX
    Explanations

    statistics related to player performance in sports

    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
    omi
    -0.07
     row
    -0.07
    row
    -0.06
    stro
    -0.06
    369
    -0.06
    res
    -0.06
    ennon
    -0.06
     values
    -0.06
     pumped
    -0.06
     unary
    -0.06
    POSITIVE LOGITS
    erez
    0.08
     ÐĶеÑĢжав
    0.07
    igure
    0.07
    ings
    0.06
    WindowText
    0.06
    _MetaData
    0.06
    arat
    0.06
    ourd
    0.06
    бÑĥдÑĮ
    0.06
    oleÄį
    0.06
    Activations Density 0.004%

    No Known Activations