© 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. 42654
    Prev
    Next
    INDEX
    Explanations

    words related to awards and recognition in the field of medicine

    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
    -nil
    -0.07
    Å©
    -0.07
    moth
    -0.07
    ardin
    -0.07
    etu
    -0.07
    äºŃ
    -0.07
    dech
    -0.07
    oru
    -0.07
    emek
    -0.07
    ijn
    -0.07
    POSITIVE LOGITS
     Sesso
    0.06
     ↵↵
    0.06
    alem
    0.06
     обл
    0.06
     FC
    0.06
     yet
    0.06
    <decltype
    0.06
     Stateless
    0.06
    itud
    0.05
     Columbus
    0.05
    Activations Density 0.022%

    No Known Activations