© 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. 44590
    Prev
    Next
    INDEX
    Explanations

    spanking methods listed

    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
    heim
    -0.11
     nose
    -0.11
    hire
    -0.10
    é¬
    -0.10
    /inc
    -0.09
    .pitch
    -0.09
     throat
    -0.09
     Bullet
    -0.09
     bullet
    -0.09
     finger
    -0.09
    POSITIVE LOGITS
     paddle
    0.20
     padd
    0.19
     spanking
    0.15
     wel
    0.14
     wield
    0.13
     beating
    0.13
     strokes
    0.13
     welt
    0.13
    -span
    0.13
     leather
    0.12
    Activations Density 0.016%

    No Known Activations