© 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. 108824
    Prev
    Next
    INDEX
    Explanations

    specific names and terms associated with creativity and its relation to mental states

    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
    iral
    -0.06
    trand
    -0.06
     Mos
    -0.06
    podob
    -0.06
    208
    -0.06
    onso
    -0.06
    velt
    -0.05
    \Notifications
    -0.05
    _attachments
    -0.05
    etro
    -0.05
    POSITIVE LOGITS
    _BINARY
    0.08
     conf
    0.07
     Leban
    0.07
    zá
    0.07
     Warp
    0.07
     Nha
    0.07
     Confederate
    0.07
    Monad
    0.07
    ê·Ģ
    0.07
    .GraphicsUnit
    0.07
    Activations Density 0.001%

    No Known Activations