© 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. 61955
    Prev
    Next
    INDEX
    Explanations

    symbols, operators, and non-latin characters

    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
     "*.
    -0.12
     '*.
    -0.10
     parenthesis
    -0.09
    è«
    -0.08
    (',')[
    -0.08
     spelling
    -0.08
     paren
    -0.08
     Consum
    -0.08
    Seeder
    -0.08
     VÆ°á»Ŀn
    -0.08
    POSITIVE LOGITS
     symbol
    0.18
    aster
    0.17
     colon
    0.16
    符
    0.15
     Aster
    0.15
     aster
    0.15
     pound
    0.15
     apost
    0.14
     dấu
    0.14
     Colon
    0.13
    Activations Density 0.222%

    No Known Activations