© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 107936
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth rates and market forecasts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    sys
    -0.07
    -datepicker
    -0.07
    erator
    -0.07
    erus
    -0.07
    ulus
    -0.07
    createQuery
    -0.07
    ëı
    -0.07
    éĢģæĸĻçĦ¡æĸĻ
    -0.07
    -await
    -0.07
    eru
    -0.07
    POSITIVE LOGITS
     growth
    0.08
     rate
    0.07
     Growth
    0.07
     faster
    0.07
     Rate
    0.06
     ÑĤемп
    0.06
    assa
    0.06
     fold
    0.06
     par
    0.06
    791
    0.06
    Activations Density 0.002%

    No Known Activations