© 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. 91541
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and biological processes

    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
    ÑĢÑĥÑĤ
    -0.08
    881
    -0.07
    جع
    -0.07
    ulace
    -0.07
    967
    -0.07
    pery
    -0.07
    resp
    -0.07
    .yy
    -0.07
    966
    -0.07
    987
    -0.07
    POSITIVE LOGITS
     rarely
    0.06
    itsu
    0.06
     overhead
    0.06
    âĢIJ
    0.06
     Healthcare
    0.06
    outu
    0.06
     synonyms
    0.05
     Batter
    0.05
     usually
    0.05
     âĢ¢
    0.05
    Activations Density 0.028%

    No Known Activations