© 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. 53702
    Prev
    Next
    INDEX
    Explanations

    preschool and kindergarten

    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
    ä¸ŃåѦ
    -0.14
    é«ĺä¸Ń
    -0.13
     adolescent
    -0.11
     adolescente
    -0.11
     kidd
    -0.11
     adult
    -0.11
     secondary
    -0.11
     Secondary
    -0.10
     elementary
    -0.10
    éĿĴ
    -0.10
    POSITIVE LOGITS
     Mont
    0.21
     Pres
    0.17
     Early
    0.16
     play
    0.16
    Pres
    0.16
     Play
    0.14
    Early
    0.14
    pres
    0.14
     nap
    0.14
     PRES
    0.13
    Activations Density 0.087%

    No Known Activations