© 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. 16072
    Prev
    Next
    INDEX
    Explanations

    female traits and stereotypes

    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
     masculine
    -0.12
     mascul
    -0.11
     masculinity
    -0.10
     mistress
    -0.09
    serter
    -0.09
     Adults
    -0.09
     Nob
    -0.09
    filesize
    -0.08
     sporting
    -0.08
     sperma
    -0.08
    POSITIVE LOGITS
     female
    0.16
     feminine
    0.16
     gir
    0.15
     pink
    0.15
     estrogen
    0.14
     Female
    0.14
     softer
    0.13
    Female
    0.13
     femin
    0.13
    female
    0.13
    Activations Density 0.093%

    No Known Activations