© 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. 2216
    Prev
    Next
    INDEX
    Explanations

    optimized code generation

    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
     compilers
    -0.11
    enez
    -0.10
     IDE
    -0.10
     jam
    -0.10
     compiler
    -0.09
     peri
    -0.09
    IDE
    -0.09
    cheid
    -0.09
    LETED
    -0.08
    dojo
    -0.08
    POSITIVE LOGITS
     code
    0.19
     Intermediate
    0.18
     instructions
    0.17
    code
    0.16
     intermediate
    0.16
     machine
    0.15
    Intermediate
    0.14
     intermedi
    0.14
     instruction
    0.14
    _listing
    0.14
    Activations Density 0.056%

    No Known Activations