© 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. 18533
    Prev
    Next
    INDEX
    Explanations

    write an IT query

    np_acts-logits-general · gemini-2.5-flash-lite

    structural cues of user-directed queries, including second-person requests, line breaks, and numbered section headings.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    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
    Negative Logits
    edia
    -0.09
    ¦æĥħ
    -0.09
    .selenium
    -0.09
     GURL
    -0.08
     Wenger
    -0.08
     GLES
    -0.08
     Blockly
    -0.08
    ìĿ´ì§Ģ
    -0.08
    DoubleClick
    -0.08
    Drupal
    -0.08
    POSITIVE LOGITS
     command
    0.10
     Dart
    0.10
     Bol
    0.10
     code
    0.09
     Dev
    0.09
     stack
    0.09
    808
    0.09
    bol
    0.09
     )\n\n\n\n\n\n\n\n
    0.09
     pent
    0.09
    Activations Density 0.231%

    No Known Activations