© 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. 96237
    Prev
    Next
    INDEX
    Explanations

    layout-related terms in a document

    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
    ylim
    -0.07
    ød
    -0.06
    abol
    -0.06
    ijke
    -0.06
    Å¡t
    -0.06
    avatar
    -0.06
    ña
    -0.06
    ensch
    -0.06
    inkle
    -0.06
    oller
    -0.06
    POSITIVE LOGITS
     Creed
    0.07
    à¹Ģà¸ķร
    0.06
    spender
    0.06
    anan
    0.06
    edla
    0.06
    .constraints
    0.06
    logging
    0.06
    M
    0.06
     Zuk
    0.06
     agreg
    0.06
    Activations Density 0.000%

    No Known Activations