© 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. 31577
    Prev
    Next
    INDEX
    Explanations

    mentions of ethnic groups and their languages

    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
    ully
    -0.07
    ë§
    -0.07
    ollow
    -0.07
    unate
    -0.07
    ury
    -0.06
    aea
    -0.06
    ussy
    -0.06
    axy
    -0.06
    utton
    -0.06
    oux
    -0.06
    POSITIVE LOGITS
     languages
    0.08
     dialect
    0.07
     Bunun
    0.07
     spoken
    0.07
     Variant
    0.07
     Leer
    0.07
     language
    0.07
     Languages
    0.07
    language
    0.07
     variant
    0.07
    Activations Density 0.015%

    No Known Activations