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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59931
    Prev
    Next
    INDEX
    Explanations

    specific scientific measurements and results related to health, particularly in the context of medical research and disease detection

    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
     (
    -0.10
     ("
    -0.07
    .").
    -0.07
     (\
    -0.07
     ([
    -0.07
     ...↵↵↵↵
    -0.07
    azy
    -0.07
     (**
    -0.07
    !↵↵
    -0.07
    uco
    -0.07
    POSITIVE LOGITS
    )
    0.09
    ),
    0.08
    ÐIJÑĢÑħÑĸв
    0.08
    ((_
    0.07
    anje
    0.07
    à¹Į)
    0.07
    )ØĮ
    0.07
    rek
    0.06
    .AutoComplete
    0.06
    à¥Ģ)
    0.06
    Activations Density 2.257%

    No Known Activations