© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118048
    Prev
    Next
    INDEX
    Explanations

    discussions around women's health and related societal challenges

    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
    æĸ
    -0.07
    æ´¾
    -0.07
    iller
    -0.07
    omer
    -0.07
    atura
    -0.07
    ει
    -0.07
    ksen
    -0.07
    mast
    -0.07
    ybrid
    -0.07
    lemen
    -0.07
    POSITIVE LOGITS
    éĨ´
    0.06
     tomorrow
    0.06
    /of
    0.06
    ìĭľìķĦ
    0.06
     moments
    0.06
     unm
    0.06
     quotid
    0.06
     seat
    0.06
     Parts
    0.06
     exh
    0.05
    Activations Density 0.038%

    No Known Activations