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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44533
    Prev
    Next
    INDEX
    Explanations

    programs, data, and activities

    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
     programmes
    -0.10
     Tome
    -0.09
     Rope
    -0.09
     اÙĦØŃÙĬ
    -0.09
    à¸Ļà¸Ń
    -0.09
    Calibri
    -0.08
    \n\n
    -0.08
     Grat
    -0.08
     Stap
    -0.08
    iam
    -0.08
    POSITIVE LOGITS
     Parad
    0.11
     Bates
    0.10
     Pioneer
    0.10
    OLS
    0.09
     Sands
    0.09
     Wend
    0.09
    602
    0.08
    (Program
    0.08
    _constants
    0.08
    Pragma
    0.08
    Activations Density 0.146%

    No Known Activations