© 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. 94626
    Prev
    Next
    INDEX
    Explanations

    notations and terminology related to gauge theories in physics

    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
    igg
    -0.07
    eldorf
    -0.07
    ului
    -0.06
     Dund
    -0.06
    ngrx
    -0.06
    oram
    -0.06
    sst
    -0.06
    rych
    -0.06
     Mission
    -0.06
    zenÃŃ
    -0.06
    POSITIVE LOGITS
    .nih
    0.07
    anian
    0.07
    алов
    0.06
    SystemService
    0.06
    WithString
    0.06
    469
    0.06
    assing
    0.06
    ä¸ĺ
    0.06
     Kidd
    0.06
     Sour
    0.06
    Activations Density 0.002%

    No Known Activations