© 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. 95972
    Prev
    Next
    INDEX
    Explanations

    grammatical elements related to species classification or nomenclature

    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
    apo
    -0.07
     Lil
    -0.07
    allo
    -0.07
    ugins
    -0.06
    ide
    -0.06
    zem
    -0.06
    zan
    -0.06
    intage
    -0.06
    664
    -0.06
    inges
    -0.06
    POSITIVE LOGITS
    alytics
    0.07
    Todd
    0.07
    ÑĢÑĸÑĩ
    0.06
     ç¥
    0.06
    елиÑĩ
    0.06
    appa
    0.06
    ç¥
    0.06
     Ãĸr
    0.06
    à¸ļà¸ļ
    0.06
    asmus
    0.06
    Activations Density 0.001%

    No Known Activations