© 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. 117576
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "is" and "and."

    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
     Mitar
    -0.07
    mlin
    -0.06
    ênh
    -0.06
    anon
    -0.06
    annes
    -0.06
    pies
    -0.06
    pull
    -0.06
    illez
    -0.06
    itol
    -0.06
    .Selenium
    -0.06
    POSITIVE LOGITS
    Filed
    0.07
    åħ±
    0.07
     unc
    0.07
    474
    0.06
    chas
    0.06
    enders
    0.06
    empor
    0.06
    ãģ¦
    0.06
     åħ±
    0.06
    Unc
    0.06
    Activations Density 0.001%

    No Known Activations