© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 54053
    Prev
    Next
    INDEX
    Explanations

    elements associated with horror or the supernatural

    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
     sao
    -0.07
    bes
    -0.07
    forth
    -0.06
    -generated
    -0.06
    ile
    -0.06
    kit
    -0.06
     Barbar
    -0.06
    urre
    -0.06
    [color
    -0.06
    -built
    -0.06
    POSITIVE LOGITS
     enough
    0.08
    $MESS
    0.07
    -looking
    0.07
    lest
    0.07
    ANNEL
    0.07
    ifix
    0.07
    grams
    0.07
    gram
    0.07
    ewan
    0.07
    avin
    0.07
    Activations Density 0.011%

    No Known Activations