© 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. 38263
    Prev
    Next
    INDEX
    Explanations

    declarations of classes in programming code

    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
    大åħ¨
    -0.07
    olini
    -0.07
    hausen
    -0.07
    ustum
    -0.06
    cean
    -0.06
    ushed
    -0.06
     jes
    -0.06
     dieta
    -0.06
    mini
    -0.06
    گاÙĩ
    -0.06
    POSITIVE LOGITS
    dera
    0.07
     Hass
    0.06
    HQ
    0.06
     Bentley
    0.06
     Ded
    0.05
     Manning
    0.05
    ingle
    0.05
    kaar
    0.05
     ÃĹ
    0.05
    ären
    0.05
    Activations Density 0.001%

    No Known Activations