© 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. 15-LLAMASCOPE-RES-131K
    11. 103134
    Prev
    Next
    INDEX
    Explanations

    statements reflecting traditional views on gender roles 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
    egin
    -0.08
    gio
    -0.07
    heel
    -0.07
     aime
    -0.07
    ëŁ
    -0.07
    chwitz
    -0.07
    ikk
    -0.07
    elo
    -0.07
    ÑĢем
    -0.07
    unate
    -0.07
    POSITIVE LOGITS
     convinced
    0.06
     premises
    0.06
     view
    0.06
     Incoming
    0.06
     notions
    0.06
     ("
    0.05
    ÛĮرÛĮ
    0.05
     consequently
    0.05
     belief
    0.05
    _this
    0.05
    Activations Density 0.031%

    No Known Activations