© 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. 42821
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements or constructs

    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
    ucus
    -0.07
    ucas
    -0.07
    -Sah
    -0.07
    rica
    -0.07
    OLA
    -0.07
    огÑĥ
    -0.07
    ined
    -0.07
    ared
    -0.07
    ÃŃ
    -0.07
     wo
    -0.06
    POSITIVE LOGITS
     fflush
    0.07
    exit
    0.07
     exit
    0.07
    ennie
    0.06
     Exit
    0.06
    erken
    0.06
    .ua
    0.06
    kim
    0.06
     Trident
    0.05
    IIIK
    0.05
    Activations Density 0.021%

    No Known Activations