© 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. 38400
    Prev
    Next
    INDEX
    Explanations

    references to methods or strategies

    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
     Hass
    -0.06
    [OF
    -0.06
    Ñıви
    -0.06
     Сов
    -0.06
    ober
    -0.06
    197
    -0.06
    ared
    -0.05
    718
    -0.05
    lef
    -0.05
    jar
    -0.05
    POSITIVE LOGITS
     Williamson
    0.08
    glob
    0.07
    globals
    0.07
     globally
    0.07
     global
    0.07
    _placeholder
    0.07
     world
    0.07
    elden
    0.06
    à¥Ĥà¤ķ
    0.06
     XCT
    0.06
    Activations Density 0.000%

    No Known Activations