© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35407
    Prev
    Next
    INDEX
    Explanations

    fines and death penalty

    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
     cin
    -0.10
     sworn
    -0.09
     Sever
    -0.09
     Hatch
    -0.09
     Arabian
    -0.09
     mile
    -0.09
     rect
    -0.09
     net
    -0.09
    gars
    -0.08
     duly
    -0.08
    POSITIVE LOGITS
     Naz
    0.10
     fine
    0.10
     ÐĿаз
    0.10
    izo
    0.10
    fine
    0.10
    Naz
    0.10
    FINE
    0.09
    EMPLARY
    0.09
    chop
    0.09
     Rodrig
    0.09
    Activations Density 0.005%

    No Known Activations