© 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. 4772
    Prev
    Next
    INDEX
    Explanations

    references to female experiences and perspectives

    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
    ffa
    -0.07
    ½æķ°
    -0.07
    rese
    -0.07
    dete
    -0.06
    æŃ¢
    -0.06
    .esp
    -0.06
    ););↵
    -0.06
    èle
    -0.06
    rypto
    -0.06
    ÑĢоÑĩ
    -0.06
    POSITIVE LOGITS
     worlds
    0.12
     world
    0.09
     environment
    0.09
     Worlds
    0.08
     environments
    0.08
     culture
    0.07
    culture
    0.07
    çݯå¢ĥ
    0.07
     prostÅĻedÃŃ
    0.07
     lives
    0.07
    Activations Density 0.095%

    No Known Activations