© 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. 62570
    Prev
    Next
    INDEX
    Explanations

    key themes related to artistic or cultural expressions and discussions

    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
    olini
    -0.07
     the
    -0.07
    ï¸ı
    -0.06
    curring
    -0.06
    /hooks
    -0.06
    thin
    -0.06
    irq
    -0.06
    the
    -0.06
    ué
    -0.06
    POSITIVE LOGITS
    arters
    0.09
    dddd
    0.08
    ceae
    0.08
    viders
    0.07
    efe
    0.07
    itmap
    0.07
    curacy
    0.07
    oze
    0.07
    SWG
    0.07
    achuset
    0.07
    Activations Density 0.027%

    No Known Activations