© 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. 39817
    Prev
    Next
    INDEX
    Explanations

    topics related to women's health issues, particularly menstrual health and 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
    affen
    -0.08
    neum
    -0.08
     kalan
    -0.07
    ï¼ł
    -0.07
    å¹¹
    -0.07
    ÃŃna
    -0.07
     رÙħضاÙĨ
    -0.07
     éĢģ
    -0.07
    efeller
    -0.07
    -earth
    -0.07
    POSITIVE LOGITS
     pain
    0.09
     Pain
    0.09
     women
    0.08
     Women
    0.08
     g
    0.07
    reesome
    0.06
     woman
    0.06
    pain
    0.06
     self
    0.06
     fertility
    0.06
    Activations Density 0.004%

    No Known Activations