© 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. 129551
    Prev
    Next
    INDEX
    Explanations

    topics related to women's health and medical 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
    ç´ł
    -0.07
    lech
    -0.06
     Normalize
    -0.06
    leck
    -0.06
    ÑĢоÑģÑĤ
    -0.06
    eprom
    -0.06
    ÙĬز
    -0.06
     Byl
    -0.06
    venes
    -0.06
    vard
    -0.06
    POSITIVE LOGITS
    enza
    0.07
     market
    0.07
    æĥ
    0.07
    æĻļ
    0.06
     markets
    0.06
     bund
    0.06
     currently
    0.06
     refr
    0.06
    askell
    0.06
     vel
    0.06
    Activations Density 0.008%

    No Known Activations