© 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. 89607
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or surprise

    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
    deen
    -0.07
    ónica
    -0.06
    omat
    -0.06
     ØŃÙĤ
    -0.06
    rvé
    -0.06
    @nate
    -0.06
    _GP
    -0.06
    inic
    -0.06
    udu
    -0.06
    asl
    -0.06
    POSITIVE LOGITS
     plus
    0.09
     also
    0.09
    ãģĿãģĹãģ¦
    0.07
    also
    0.07
     ê·¸ë¦¬ê³ł
    0.07
     także
    0.07
     note
    0.07
     occasionally
    0.07
    LOY
    0.07
     juga
    0.07
    Activations Density 0.005%

    No Known Activations