© 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. 53718
    Prev
    Next
    INDEX
    Explanations

    references to character interactions and journeys in a narrative context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    otre
    -0.07
    enson
    -0.07
     ÑĢоз
    -0.06
    indicator
    -0.06
     Kansas
    -0.06
    ÄĽle
    -0.06
    jerne
    -0.06
    axter
    -0.06
     Jedi
    -0.06
    ancel
    -0.06
    POSITIVE LOGITS
     Levi
    0.06
    å¼
    0.06
    ppelin
    0.06
     Clarkson
    0.06
     IDs
    0.06
     towns
    0.06
     Brock
    0.06
     Wend
    0.06
    ipe
    0.06
     town
    0.05
    Activations Density 0.006%

    No Known Activations