© 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. 37464
    Prev
    Next
    INDEX
    Explanations

    code control flow

    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
    return
    -0.15
     return
    -0.14
    -return
    -0.13
    Return
    -0.13
    _return
    -0.12
     Return
    -0.12
    .return
    -0.11
     RETURN
    -0.11
    è¿ĶåĽŀ
    -0.11
    (return
    -0.11
    POSITIVE LOGITS
     if
    0.15
     continue
    0.14
     temp
    0.13
     tmp
    0.12
     print
    0.12
    \tif
    0.12
     Temp
    0.12
    continue
    0.12
    Continue
    0.12
    temp
    0.11
    Activations Density 0.040%

    No Known Activations