© 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. 89668
    Prev
    Next
    INDEX
    Explanations

    connections between obesity, weight, and physical health

    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
    dete
    -0.08
    echa
    -0.08
    ulg
    -0.07
    nero
    -0.07
    eld
    -0.07
    eldon
    -0.07
    yme
    -0.07
    Īĺ
    -0.07
    UTC
    -0.07
    .nano
    -0.07
    POSITIVE LOGITS
     medical
    0.07
     mor
    0.06
     obese
    0.06
     Sho
    0.06
     fatty
    0.06
     BMI
    0.06
     adip
    0.06
    BMI
    0.06
     scales
    0.06
     insulin
    0.06
    Activations Density 0.008%

    No Known Activations