© 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. 24213
    Prev
    Next
    INDEX
    Explanations

    code break statements

    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
     Mend
    -0.10
     ï½
    -0.10
    æī£
    -0.09
    ReturnType
    -0.09
     Returning
    -0.09
     Circular
    -0.09
     Returned
    -0.09
    _UNUSED
    -0.08
    Shutdown
    -0.08
    hil
    -0.08
    POSITIVE LOGITS
     break
    0.73
    break
    0.50
    \tbreak
    0.47
     Break
    0.42
     breaks
    0.40
    -break
    0.38
    Break
    0.35
     continue
    0.31
    _break
    0.31
     BREAK
    0.30
    Activations Density 0.026%

    No Known Activations