© 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. 9-LLAMASCOPE-RES-131K
    11. 97589
    Prev
    Next
    INDEX
    Explanations

    phrases related to scoring and statistics 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
    riba
    -0.07
    quire
    -0.07
    ereotype
    -0.07
     cán
    -0.07
    atern
    -0.07
    ẽ
    -0.07
    stoff
    -0.07
    utar
    -0.06
    geber
    -0.06
    wig
    -0.06
    POSITIVE LOGITS
    conds
    0.07
    ³
    0.07
     commun
    0.06
    .synthetic
    0.06
    errat
    0.06
     æ¾
    0.06
     Auss
    0.06
    uenta
    0.06
     Tech
    0.06
    ائÙģ
    0.06
    Activations Density 0.002%

    No Known Activations