© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 64594
    Prev
    Next
    INDEX
    Explanations

    return statements in code

    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
    antanamo
    -0.09
    Ě
    -0.08
    ä¹İ
    -0.08
     Haram
    -0.08
    752
    -0.08
    ШÐIJ
    -0.08
     stranger
    -0.08
    ammers
    -0.08
     Returned
    -0.08
    Ē
    -0.08
    POSITIVE LOGITS
     return
    0.11
    onis
    0.10
     pass
    0.10
     Wag
    0.09
    pass
    0.09
    \treturn
    0.09
    itu
    0.09
    ivers
    0.09
    return
    0.08
     Neb
    0.08
    Activations Density 0.030%

    No Known Activations