© 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. 38508
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or settings related to cultural or artistic contexts

    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
    ypo
    -0.06
    elo
    -0.06
    abus
    -0.06
    æ¨
    -0.06
    ÙĤÙĬØ©
    -0.06
     provid
    -0.06
    deal
    -0.06
    referer
    -0.06
     contrast
    -0.06
    otify
    -0.06
    POSITIVE LOGITS
     Maya
    0.10
     py
    0.09
    mayan
    0.08
     temples
    0.08
     glyph
    0.08
    /py
    0.07
    uten
    0.07
    Mexico
    0.07
     glyphs
    0.07
     Mexico
    0.07
    Activations Density 0.014%

    No Known Activations