© 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. 1415
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks and colons

    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
    áy
    -0.07
    ache
    -0.07
     NÄĽm
    -0.07
     ()č↵
    -0.06
    áo
    -0.06
    uku
    -0.06
    rama
    -0.06
     passes
    -0.06
    awan
    -0.06
     quits
    -0.06
    POSITIVE LOGITS
    0.07
    rve
    0.07
    377
    0.07
     !***
    0.07
    scaled
    0.07
     EntityState
    0.07
     Lorem
    0.07
    groupon
    0.07
    GRES
    0.06
    ColumnsMode
    0.06
    Activations Density 0.019%

    No Known Activations