© 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. 46107
    Prev
    Next
    INDEX
    Explanations

    programming method calls

    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
    Negative Logits
    assing
    -0.10
    =
    -0.10
    yat
    -0.09
    AndWait
    -0.09
    OrUpdate
    -0.09
    (AdapterView
    -0.09
     =
    -0.09
    -0.09
     venez
    -0.09
     Laud
    -0.09
    POSITIVE LOGITS
    ().
    0.19
    ()
    0.16
    ()[
    0.16
    /Set
    0.12
    ()\n
    0.12
    .return
    0.11
    ('
    0.11
    ÐIJÑĢÑħÑĸв
    0.10
    ("
    0.10
    ();\n
    0.10
    Activations Density 0.041%

    No Known Activations