© 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. 14840
    Prev
    Next
    INDEX
    Explanations

    gender discrimination misogyny

    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
     homosexual
    -0.13
     homo
    -0.11
     gay
    -0.11
     homosexuality
    -0.11
     Gay
    -0.11
    gay
    -0.11
    -gay
    -0.10
     homosex
    -0.10
     sodom
    -0.10
     Lesbian
    -0.10
    POSITIVE LOGITS
     gender
    0.27
     Gender
    0.25
    Gender
    0.24
     male
    0.24
     patri
    0.23
    gender
    0.23
     mys
    0.22
    .gender
    0.22
     men
    0.22
     Patri
    0.22
    Activations Density 0.203%

    No Known Activations