© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 95313
    Prev
    Next
    INDEX
    Explanations

    discussions about women's health and societal expectations

    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
    ringe
    -0.07
    ague
    -0.07
    issen
    -0.07
    akte
    -0.07
    normal
    -0.07
    rlen
    -0.07
    amba
    -0.07
    steen
    -0.07
    dge
    -0.07
    chten
    -0.06
    POSITIVE LOGITS
     females
    0.09
     women
    0.09
     Women
    0.08
     differences
    0.08
     female
    0.08
    Women
    0.08
    Female
    0.08
     WOM
    0.08
     men
    0.08
    women
    0.07
    Activations Density 0.013%

    No Known Activations