© 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. 91699
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly in a structured or tabular format

    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
    imuth
    -0.06
    102
    -0.06
     Zheng
    -0.06
    nell
    -0.06
    unce
    -0.05
    617
    -0.05
    outh
    -0.05
     Kit
    -0.05
     ins
    -0.05
    asar
    -0.05
    POSITIVE LOGITS
    ogram
    0.07
     пÑĢиклад
    0.07
    _Syntax
    0.07
    .pipe
    0.07
    å¿ľ
    0.07
    ICollection
    0.07
    itably
    0.07
    kad
    0.07
    skins
    0.07
    okable
    0.07
    Activations Density 0.071%

    No Known Activations