© 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. 104890
    Prev
    Next
    INDEX
    Explanations

    references to gender, particularly focusing on the words "man" and "woman."

    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
    ira
    -0.08
     åĨ
    -0.07
    iran
    -0.07
    даÑĤ
    -0.06
    صÙĦ
    -0.06
    oris
    -0.06
    DEX
    -0.06
    alez
    -0.06
    taire
    -0.06
     nid
    -0.06
    POSITIVE LOGITS
     woman
    0.08
     man
    0.07
    hood
    0.07
    nb
    0.07
    ungs
    0.06
    Woman
    0.06
     Woman
    0.06
    ifest
    0.06
    oir
    0.06
    anch
    0.06
    Activations Density 0.030%

    No Known Activations