© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    curly braces, parentheses, square brackets

    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
     prepend
    -0.11
    âĢİ
    -0.10
     Harper
    -0.09
     abbreviation
    -0.09
     italic
    -0.09
    spacer
    -0.09
     Tribute
    -0.08
     hors
    -0.08
    artner
    -0.08
     Corm
    -0.08
    POSITIVE LOGITS
     square
    0.27
     brackets
    0.24
    æĭ¬
    0.23
     Square
    0.21
     braces
    0.20
    square
    0.20
    ê´
    0.20
    Br
    0.20
     Br
    0.19
    _br
    0.18
    Activations Density 0.183%

    No Known Activations