© 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. 77170
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and records related to 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
    abbo
    -0.08
    ç¬
    -0.07
    taire
    -0.06
    ÏĦιν
    -0.06
    RITE
    -0.06
    ationToken
    -0.06
     Dough
    -0.06
    esel
    -0.06
    owler
    -0.06
    lobals
    -0.06
    POSITIVE LOGITS
    iku
    0.07
    gers
    0.07
     most
    0.07
     including
    0.06
    utt
    0.06
    kov
    0.06
     compared
    0.06
    incl
    0.06
    ãģĨãģ¡
    0.06
    /REC
    0.06
    Activations Density 0.014%

    No Known Activations