© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35458
    Prev
    Next
    INDEX
    Explanations

    declaration and dynamic programming

    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
     Hatch
    -0.09
     NÄĽk
    -0.09
    fol
    -0.09
    InstanceId
    -0.08
    jour
    -0.08
    flake
    -0.08
     NÄĽkter
    -0.08
     Eag
    -0.08
     bul
    -0.08
     Hawkins
    -0.08
    POSITIVE LOGITS
     code
    0.15
     program
    0.12
    代çłģ
    0.11
    uze
    0.11
    .setCode
    0.10
     íĶĦë¡ľê·¸ëŀ¨
    0.10
     programs
    0.09
     código
    0.09
     programme
    0.09
     data
    0.09
    Activations Density 0.097%

    No Known Activations