© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 463
    Prev
    Next
    INDEX
    Explanations

    spanking and discipline

    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
    rang
    -0.11
    indr
    -0.11
     sop
    -0.10
     Bez
    -0.10
    bish
    -0.10
    kills
    -0.10
     Cage
    -0.09
     indict
    -0.09
    bjerg
    -0.09
     kill
    -0.09
    POSITIVE LOGITS
     corpor
    0.26
     spanking
    0.24
     padd
    0.20
    Span
    0.20
     discipline
    0.20
     Corpor
    0.20
     span
    0.20
     paddle
    0.19
    -span
    0.19
    span
    0.19
    Activations Density 0.052%

    No Known Activations