© 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. 57214
    Prev
    Next
    INDEX
    Explanations

    female pronoun and identity

    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
     himself
    -0.33
     his
    -0.25
     boy
    -0.24
    him
    -0.24
     brother
    -0.22
     ông
    -0.22
     boys
    -0.21
     businessman
    -0.21
     him
    -0.21
    çĶ·åŃIJ
    -0.21
    POSITIVE LOGITS
     herself
    0.56
     woman
    0.41
     her
    0.39
     she
    0.37
    woman
    0.34
     hers
    0.31
    她
    0.31
     girl
    0.30
     haar
    0.29
    she
    0.28
    Activations Density 0.623%

    No Known Activations