© 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. 55175
    Prev
    Next
    INDEX
    Explanations

    differences or disagreements

    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
    uve
    -0.11
    errick
    -0.10
     discredit
    -0.10
    isle
    -0.09
    andles
    -0.09
    /Dk
    -0.09
     inconsistency
    -0.09
     friendships
    -0.09
     incest
    -0.09
    ewise
    -0.08
    POSITIVE LOGITS
     differences
    0.52
     difference
    0.45
     Differences
    0.41
    difference
    0.37
    å·®
    0.36
    ifferences
    0.35
     Difference
    0.35
    Difference
    0.34
    _difference
    0.29
     diffé
    0.28
    Activations Density 0.091%

    No Known Activations