© 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. 80813
    Prev
    Next
    INDEX
    Explanations

    specific formatting and structure in written documents, particularly focusing on headers, footers, and annotations

    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
    iê
    -0.07
    lâm
    -0.07
     Yüz
    -0.07
    òng
    -0.07
    xon
    -0.07
    iteDatabase
    -0.06
    .qual
    -0.06
    оÑĢе
    -0.06
    WSTR
    -0.06
    AIM
    -0.06
    POSITIVE LOGITS
    _A
    0.10
    .A
    0.10
     A
    0.10
    A
    0.09
     ìķĦ
    0.09
    ÂłA
    0.09
     ãĤ¢
    0.09
    _a
    0.08
     nouvel
    0.08
    ãĤ¢
    0.08
    Activations Density 0.942%

    No Known Activations