© 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. 19211
    Prev
    Next
    INDEX
    Explanations

    "people", "Pluto", "API", "noodles"

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

    text fragments that appear in structured lists or data formats, particularly after colons, asterisks, or in enumerated items.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @yooniel31
    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
    :\n
    -0.11
    -0.11
     blah
    -0.09
    :\n\n
    -0.09
     *&
    -0.09
    .hh
    -0.09
    ::\n\n
    -0.09
     Prel
    -0.09
     Bast
    -0.09
    bastian
    -0.09
    POSITIVE LOGITS
     Note
    0.13
     NOTE
    0.13
     note
    0.13
     )\n\n\n\n\n\n\n\n
    0.11
    Note
    0.11
    $MESS
    0.11
     fetisch
    0.10
     âĢ»
    0.10
     *</
    0.10
    NOTE
    0.10
    Activations Density 0.215%

    No Known Activations