© 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. 40799
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to writing systems and their characteristics

    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
     respectively
    -0.06
    ib
    -0.06
    org
    -0.06
     whereas
    -0.06
    ä¸ĬäºĨ
    -0.06
    776
    -0.06
    ire
    -0.06
    blings
    -0.06
     -
    -0.05
    ops
    -0.05
    POSITIVE LOGITS
    人ãģ¯
    0.09
     же
    0.09
    ByUsername
    0.08
    avou
    0.07
     dán
    0.07
    ãģ¡ãģ¯
    0.07
    ,__
    0.07
    ìĿ¸ìĿĢ
    0.07
     ayrıca
    0.07
     ìĤ¬ëŀĮìĿĢ
    0.07
    Activations Density 0.032%

    No Known Activations