© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 26414
    Prev
    Next
    INDEX
    Explanations

    code return 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
     otherwise
    -0.17
     Otherwise
    -0.15
    Otherwise
    -0.14
    otherwise
    -0.13
    åIJ¦
    -0.13
     OTHERWISE
    -0.12
    imer
    -0.10
     jinak
    -0.10
     GPLv
    -0.09
    #elif
    -0.09
    POSITIVE LOGITS
     endwhile
    0.10
    rans
    0.10
    wing
    0.10
    SupportedContent
    0.10
    oman
    0.09
    enth
    0.09
     glEnd
    0.09
     Buen
    0.09
    imd
    0.09
     Ngh
    0.09
    Activations Density 0.020%

    No Known Activations