© 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. 9-LLAMASCOPE-RES-131K
    11. 94128
    Prev
    Next
    INDEX
    Explanations

    references to urinary conditions and related medical terminology

    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
    readcr
    -0.08
    loth
    -0.08
    ikat
    -0.07
    ë¡Ģ
    -0.07
     Svens
    -0.07
    ivé
    -0.07
    "urls
    -0.07
    erif
    -0.07
     @"↵
    -0.07
    çĦ¶
    -0.07
    POSITIVE LOGITS
     pil
    0.06
     atom
    0.06
     bomb
    0.06
     atomic
    0.06
     dep
    0.06
     Atomic
    0.05
    ãĤº
    0.05
    ени
    0.05
     formed
    0.05
     filled
    0.05
    Activations Density 0.001%

    No Known Activations