© 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. 30965
    Prev
    Next
    INDEX
    Explanations

    don't hesitate

    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
    eh
    -0.11
     Nathan
    -0.10
    orsi
    -0.10
    anship
    -0.10
    allen
    -0.09
    EST
    -0.09
     Ruf
    -0.09
    hen
    -0.09
     Barcl
    -0.09
     Kris
    -0.08
    POSITIVE LOGITS
    itez
    0.15
     hesitation
    0.14
     hesitate
    0.14
     pas
    0.12
    quez
    0.10
     Pas
    0.10
     hes
    0.10
    itation
    0.10
    hes
    0.10
    itating
    0.10
    Activations Density 0.005%

    No Known Activations