© 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. 93467
    Prev
    Next
    INDEX
    Explanations

    references to economic statistics related to commodities and resources

    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
    âĻ¡
    -0.14
    (æĹ¥
    -0.14
    #ad
    -0.13
    (çģ«
    -0.12
    ï¼ĭ
    -0.12
     dilig
    -0.12
    каÑģ
    -0.12
    .↵↵↵↵↵↵↵↵
    -0.12
    .DropDown
    -0.12
     trh
    -0.12
    POSITIVE LOGITS
    ..↵
    0.09
    âĢ¦↵
    0.09
     [âĢ¦]↵
    0.07
    <|end_of_text|>
    0.07
    Âł
    0.07
    x
    0.07
     âĢ¦↵
    0.07
    Âł↵
    0.06
    .↵
    0.06
    0.06
    Activations Density 0.034%

    No Known Activations