© 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. 39250
    Prev
    Next
    INDEX
    Explanations

    references to gender-related issues and biases

    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
    adera
    -0.08
    ól
    -0.07
    duk
    -0.07
    oft
    -0.07
    _SENT
    -0.07
    ublish
    -0.07
    วà¸ģ
    -0.07
    _POINT
    -0.06
    ãĤ£
    -0.06
    ader
    -0.06
    POSITIVE LOGITS
     etc
    0.06
    ÐĴÐŀ
    0.06
    Mass
    0.05
    SEP
    0.05
    ples
    0.05
     unless
    0.05
     ÐĿаз
    0.05
    tex
    0.05
    --[[
    0.05
    mediate
    0.05
    Activations Density 0.054%

    No Known Activations