© 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. 31892
    Prev
    Next
    INDEX
    Explanations

    sin, original sin, committed

    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
     неж
    -0.09
     Obl
    -0.09
    marvin
    -0.09
     Чи
    -0.09
     ÑĥÑħ
    -0.09
    lij
    -0.09
     Bere
    -0.09
    alendar
    -0.09
    ukes
    -0.09
    æŃ
    -0.09
    POSITIVE LOGITS
     sin
    0.38
     sins
    0.31
    sin
    0.28
    .sin
    0.27
     committed
    0.26
     Sin
    0.26
     crime
    0.25
    (sin
    0.25
    罪
    0.25
    Sin
    0.24
    Activations Density 0.102%

    No Known Activations