© 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. 70761
    Prev
    Next
    INDEX
    Explanations

    phrases related to health conditions and their management

    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
    вÑĸлÑĮ
    -0.07
    ITTE
    -0.06
    chine
    -0.06
    gom
    -0.06
    CTL
    -0.06
    uien
    -0.06
    idon
    -0.06
    eyle
    -0.06
    ritz
    -0.06
    éĢģæĸĻçĦ¡æĸĻ
    -0.06
    POSITIVE LOGITS
    Ñĩа
    0.08
    aines
    0.07
    ank
    0.07
    ég
    0.07
    enan
    0.07
    ince
    0.07
    419
    0.06
    asu
    0.06
    {}'.
    0.06
    utterstock
    0.06
    Activations Density 0.059%

    No Known Activations