© 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. 72199
    Prev
    Next
    INDEX
    Explanations

    themes related to women's stories and their representation

    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
    eya
    -0.08
    ohn
    -0.07
    foil
    -0.07
    asad
    -0.07
    iment
    -0.07
     sinks
    -0.07
    utra
    -0.07
    ics
    -0.07
    zung
    -0.07
    _AA
    -0.06
    POSITIVE LOGITS
     story
    0.09
     stories
    0.09
     message
    0.08
     Story
    0.07
    message
    0.07
    Stories
    0.07
     Stories
    0.07
     STORY
    0.07
    Story
    0.07
    story
    0.07
    Activations Density 0.111%

    No Known Activations