© 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. 29444
    Prev
    Next
    INDEX
    Explanations

    recursive descent parser

    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
     synt
    -0.09
    ymm
    -0.09
     amp
    -0.09
    UFFIX
    -0.08
    _logic
    -0.08
    wargs
    -0.08
     Agency
    -0.08
     Laz
    -0.08
     Lingu
    -0.08
     sno
    -0.08
    POSITIVE LOGITS
     token
    0.19
     tokens
    0.18
     Token
    0.18
     tok
    0.17
     productions
    0.16
     AST
    0.16
     rule
    0.15
     Tokens
    0.15
     Bison
    0.15
    tokens
    0.14
    Activations Density 0.088%

    No Known Activations