© 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. 2352
    Prev
    Next
    INDEX
    Explanations

    contrasting two options

    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
     åIJ
    -0.10
     neither
    -0.10
     Hoover
    -0.09
    lette
    -0.09
    uly
    -0.09
    isce
    -0.09
    ores
    -0.08
    FI
    -0.08
     refuse
    -0.08
     sever
    -0.08
    POSITIVE LOGITS
     being
    0.15
     necessarily
    0.13
     vice
    0.12
    /as
    0.12
     having
    0.10
     just
    0.10
     اÛĮÙĨÚ©Ùĩ
    0.10
    being
    0.10
    vice
    0.10
     sendo
    0.09
    Activations Density 0.028%

    No Known Activations