Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 74996
    Prev
    Next
    INDEX
    Explanations

    issues related to women's health and the challenges in accessing health services

    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
    phe
    -0.06
     hopefully
    -0.06
    nant
    -0.06
    axon
    -0.06
    ungan
    -0.06
    ved
    -0.06
    ł
    -0.06
    èº
    -0.06
    ebo
    -0.06
     ÐŁÐ¾ÑģÑĤ
    -0.06
    POSITIVE LOGITS
     often
    0.08
     souvent
    0.07
    often
    0.07
    lags
    0.07
     lacks
    0.07
     henüz
    0.07
     hasn
    0.07
     neither
    0.07
     Despite
    0.07
     rarely
    0.07
    Activations Density 0.048%

    No Known Activations