© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 19263
    Prev
    Next
    INDEX
    Explanations

    sexual orientation and gender identity

    np_acts-logits-general · gemini-2.5-flash-lite

    lists or enumerations, particularly with commas separating items.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @yooniel31
    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
    Negative Logits
     follando
    -0.12
     Interracial
    -0.12
     Pig
    -0.10
     homophobic
    -0.10
     homosexuals
    -0.10
    Unnamed
    -0.10
     hlad
    -0.09
     Chun
    -0.09
    FindObject
    -0.09
     Gui
    -0.09
    POSITIVE LOGITS
     neut
    0.25
     trans
    0.25
     fluid
    0.20
     Trans
    0.20
     transgender
    0.20
    Trans
    0.18
     Fluid
    0.17
    trans
    0.17
     tran
    0.17
    -binary
    0.17
    Activations Density 0.080%

    No Known Activations