© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 25078
    Prev
    Next
    INDEX
    Explanations

    describing marital status and appearance

    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
     boyfriend
    -0.19
     Girlfriend
    -0.19
     girlfriend
    -0.19
     Dating
    -0.17
     dating
    -0.17
    Dating
    -0.15
     unmarried
    -0.15
     fiance
    -0.14
    æģĭ
    -0.14
     celib
    -0.13
    POSITIVE LOGITS
     husband
    0.33
     wife
    0.30
    夫
    0.28
    ä¸Ī夫
    0.28
    wife
    0.26
     Husband
    0.26
     husbands
    0.25
    妻
    0.25
     married
    0.25
     Wife
    0.25
    Activations Density 0.117%

    No Known Activations