© 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. 40524
    Prev
    Next
    INDEX
    Explanations

    statistical references and metrics related to sports outcomes

    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
    EGA
    -0.07
    ORA
    -0.07
    ora
    -0.07
    ÑĪев
    -0.07
    acob
    -0.06
    ẩm
    -0.06
    alat
    -0.06
    oled
    -0.06
    ynet
    -0.06
    agger
    -0.06
    POSITIVE LOGITS
    IRMWARE
    0.08
    iedo
    0.07
    mut
    0.07
    reau
    0.06
    /down
    0.06
    lep
    0.06
     Fus
    0.06
    añ
    0.06
     Acres
    0.06
     Sachs
    0.06
    Activations Density 0.002%

    No Known Activations