© 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. 50184
    Prev
    Next
    INDEX
    Explanations

    write SQL vs use

    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
    缴æİ¥
    -0.12
     einfach
    -0.12
     simplement
    -0.12
    ç®Ģåįķ
    -0.12
     simply
    -0.12
     plain
    -0.12
     direct
    -0.12
     simpler
    -0.10
    pes
    -0.10
     ÄijÆ¡n
    -0.10
    POSITIVE LOGITS
     via
    0.12
     indirect
    0.10
     formal
    0.09
    rahim
    0.09
    .newBuilder
    0.09
     Gian
    0.09
    875
    0.08
     ë¬
    0.08
    ç¨į
    0.08
     Ä°mpar
    0.08
    Activations Density 0.130%

    No Known Activations