© 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. 9-LLAMASCOPE-RES-131K
    11. 94151
    Prev
    Next
    INDEX
    Explanations

    questions related to cultural topics, specifically related to ancient Greece and its mythology

    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
    otti
    -0.06
    gether
    -0.06
    ÑĪкÑĥ
    -0.06
     flank
    -0.06
    566
    -0.05
    ingo
    -0.05
    æ¹¾
    -0.05
     Rank
    -0.05
    alogy
    -0.05
    Ç
    -0.05
    POSITIVE LOGITS
    $MESS
    0.08
    umbo
    0.08
     Dün
    0.07
    ůl
    0.07
    ABCDE
    0.07
     Pazar
    0.07
    мÑĸнÑĸ
    0.07
     ={↵
    0.07
    ucch
    0.07
    ãĥĸãĥª
    0.07
    Activations Density 0.002%

    No Known Activations