© 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. 41946
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements and quantities

    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
    buz
    -0.08
    uzzi
    -0.07
    /pm
    -0.07
    寸
    -0.07
    orum
    -0.07
     Werner
    -0.06
     Horton
    -0.06
    "urls
    -0.06
    ätz
    -0.06
     spol
    -0.06
    POSITIVE LOGITS
    637
    0.07
    _deriv
    0.07
    toc
    0.06
    617
    0.06
     m
    0.06
     Schneider
    0.06
    ystone
    0.06
    abra
    0.06
     Roe
    0.06
     Mint
    0.06
    Activations Density 0.022%

    No Known Activations