© 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. 39723
    Prev
    Next
    INDEX
    Explanations

    mentions of a child

    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
     infancy
    -0.16
     youthful
    -0.12
    çĶ·äºº
    -0.12
     teenage
    -0.11
    -men
    -0.11
     hombres
    -0.11
     Männer
    -0.11
     men
    -0.11
     juvenile
    -0.11
     Infant
    -0.10
    POSITIVE LOGITS
     child
    0.56
    child
    0.38
     kid
    0.35
     Child
    0.35
    (child
    0.33
     childs
    0.32
    åŃ©åŃIJ
    0.31
    \tchild
    0.30
    Child
    0.30
    -child
    0.29
    Activations Density 0.132%

    No Known Activations