© 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. 30742
    Prev
    Next
    INDEX
    Explanations

    references to web pages and online resources

    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
    ENS
    -0.06
    جد
    -0.06
    åº
    -0.06
     TITLE
    -0.06
     pii
    -0.06
    spi
    -0.05
    apid
    -0.05
    oro
    -0.05
    iku
    -0.05
    endra
    -0.05
    POSITIVE LOGITS
    erte
    0.07
    urgeon
    0.07
    ajaran
    0.07
    /cop
    0.07
    AttributeName
    0.07
    arked
    0.07
    /GPL
    0.07
    avras
    0.07
    _makeConstraints
    0.06
    aterangepicker
    0.06
    Activations Density 0.001%

    No Known Activations