© 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. 43641
    Prev
    Next
    INDEX
    Explanations

    Python pass statement

    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
     apr
    -0.10
    INFRINGEMENT
    -0.09
    aires
    -0.08
     Wass
    -0.08
    /fl
    -0.08
    ony
    -0.08
    ottenham
    -0.08
    ael
    -0.08
    erm
    -0.08
    .cc
    -0.08
    POSITIVE LOGITS
     pass
    0.69
    pass
    0.50
     Pass
    0.40
     passes
    0.35
    \tpass
    0.33
    -pass
    0.32
    _pass
    0.30
    Pass
    0.29
    (pass
    0.29
     PASS
    0.28
    Activations Density 0.054%

    No Known Activations