© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29455
    Prev
    Next
    INDEX
    Explanations

    male/female partners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wife
    -0.39
     Wife
    -0.37
    妻
    -0.33
     wives
    -0.32
    wife
    -0.31
    -wife
    -0.29
     esposa
    -0.23
     vợ
    -0.23
    wives
    -0.20
     girlfriend
    -0.20
    POSITIVE LOGITS
     boyfriend
    0.40
     husband
    0.35
     male
    0.35
     men
    0.33
     husbands
    0.31
     мÑĥж
    0.31
     males
    0.30
     Husband
    0.29
     chá»ĵng
    0.28
    ä¸Ī夫
    0.28
    Activations Density 0.266%

    No Known Activations