© 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. 15-LLAMASCOPE-RES-131K
    11. 90653
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries and health conditions

    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
    Ñĥл
    -0.07
    hap
    -0.06
    udson
    -0.06
    pez
    -0.06
    adera
    -0.06
    issen
    -0.06
    iez
    -0.06
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.06
    bery
    -0.06
    ÑĮ
    -0.06
    POSITIVE LOGITS
     --------↵
    0.07
     Boyd
    0.07
    aleigh
    0.07
    insk
    0.06
     Busy
    0.06
    erek
    0.06
    uze
    0.06
    ensing
    0.06
    jac
    0.06
    _BUSY
    0.06
    Activations Density 0.015%

    No Known Activations