© 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. 105119
    Prev
    Next
    INDEX
    Explanations

    information related to health measurement and tracking systems

    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
    UGIN
    -0.06
     Listings
    -0.06
     uncertainties
    -0.06
    oras
    -0.06
    loid
    -0.06
     Waters
    -0.06
    æĨ
    -0.06
    URITY
    -0.06
    _print
    -0.06
     disse
    -0.06
    POSITIVE LOGITS
     data
    0.09
    æķ°æį®
    0.08
    data
    0.07
     collected
    0.07
     records
    0.07
    unma
    0.07
     запиÑģ
    0.07
    -data
    0.07
    turnstile
    0.07
    .collect
    0.06
    Activations Density 0.037%

    No Known Activations