© 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. 93953
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and events

    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
     ><?
    -0.07
     detail
    -0.06
    yc
    -0.06
    erm
    -0.06
    etler
    -0.06
     medium
    -0.06
    uong
    -0.06
     Millet
    -0.06
    wu
    -0.06
    311
    -0.06
    POSITIVE LOGITS
    ëħ
    0.07
    duk
    0.07
    ystick
    0.06
     *----------------------------------------------------------------
    0.06
    κÏĮ
    0.06
    ingleton
    0.06
    Bind
    0.06
    plx
    0.06
     Gale
    0.06
    ãģŁãģı
    0.06
    Activations Density 0.010%

    No Known Activations