© 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. 58661
    Prev
    Next
    INDEX
    Explanations

    girl female gender

    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
    lek
    -0.10
    ycz
    -0.09
    fitness
    -0.09
    _scripts
    -0.09
     Interracial
    -0.09
     racist
    -0.09
    Disappear
    -0.09
     Ob
    -0.09
     abs
    -0.09
     Tribe
    -0.08
    POSITIVE LOGITS
     female
    0.23
     Female
    0.18
    female
    0.18
    Female
    0.15
     gender
    0.15
     females
    0.14
    âĻĢ
    0.14
     Binary
    0.14
     binary
    0.14
     Gender
    0.14
    Activations Density 0.050%

    No Known Activations