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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93711
    Prev
    Next
    INDEX
    Explanations

    mentions of women's achievements and contributions across various fields

    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
    juana
    -0.06
    cade
    -0.06
    OLA
    -0.06
    raction
    -0.06
    oni
    -0.06
    á»Ļng
    -0.06
     EXPER
    -0.06
    омеÑĢ
    -0.06
    preci
    -0.06
    iswa
    -0.06
    POSITIVE LOGITS
    ANDLE
    0.08
     {?>↵
    0.07
    Scaled
    0.07
    owns
    0.07
     medicine
    0.06
     disproportionate
    0.06
    WebService
    0.06
    ابط
    0.06
     service
    0.06
    roles
    0.06
    Activations Density 0.032%

    No Known Activations