© 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. 87373
    Prev
    Next
    INDEX
    Explanations

    repetitive conjunctions in the text

    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
    astos
    -0.08
    imli
    -0.08
    Ymd
    -0.07
    Å¡et
    -0.07
    portlet
    -0.07
    öl
    -0.07
    jsonp
    -0.07
    /Dk
    -0.07
    enu
    -0.07
    .GraphicsUnit
    -0.07
    POSITIVE LOGITS
    arty
    0.08
    ohn
    0.08
    UME
    0.07
    mo
    0.06
    uc
    0.06
    Trivia
    0.06
     none
    0.06
    _DECL
    0.06
     WEB
    0.06
    LOTS
    0.06
    Activations Density 0.063%

    No Known Activations