© 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. 63395
    Prev
    Next
    INDEX
    Explanations

    attractive or impressive qualities for women

    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
     worthwhile
    -0.10
     blonde
    -0.10
    914
    -0.09
     stup
    -0.09
     Blonde
    -0.09
     reputation
    -0.09
    eder
    -0.09
     amusement
    -0.09
     Blond
    -0.09
     Lounge
    -0.09
    POSITIVE LOGITS
     attractive
    0.29
    tractive
    0.23
     appeal
    0.22
     appealing
    0.20
     magnetic
    0.20
     Appeal
    0.19
     hấp
    0.19
     attractiveness
    0.18
     à¤Ĩà¤ķर
    0.18
    attr
    0.17
    Activations Density 0.093%

    No Known Activations