© 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. 5578
    Prev
    Next
    INDEX
    Explanations

    statistical information about sports performance metrics

    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
    ãģ«ãģĭ
    -0.07
    URT
    -0.07
    沿
    -0.06
    elez
    -0.06
    356
    -0.06
    arkin
    -0.06
    :///
    -0.06
     perhaps
    -0.06
    VRT
    -0.05
     mach
    -0.05
    POSITIVE LOGITS
    ardown
    0.06
    HING
    0.06
    ιÏİ
    0.06
    boru
    0.06
    klady
    0.06
    idy
    0.06
     consc
    0.06
    htag
    0.06
    kiem
    0.06
    traction
    0.06
    Activations Density 0.015%

    No Known Activations