© 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. 56026
    Prev
    Next
    INDEX
    Explanations

    female pronouns

    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
     seule
    -0.12
    /he
    -0.11
     sheer
    -0.11
     бÑĭла
    -0.11
     ihnen
    -0.11
    pher
    -0.11
     должна
    -0.10
     бÑĥла
    -0.10
    athing
    -0.10
    esh
    -0.10
    POSITIVE LOGITS
     her
    0.54
     hers
    0.53
     she
    0.51
    她
    0.47
     haar
    0.43
    彼女
    0.42
    她çļĦ
    0.41
     henne
    0.40
     jejÃŃ
    0.40
     ella
    0.38
    Activations Density 0.237%

    No Known Activations