© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 979
    Prev
    Next
    INDEX
    Explanations

    .set, .add, object creation

    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
    729
    -0.11
    .removeEventListener
    -0.11
     Claud
    -0.10
    .setViewport
    -0.10
    coma
    -0.09
     wreck
    -0.09
    .sendRedirect
    -0.09
     êµ
    -0.09
    .unbind
    -0.09
    setEnabled
    -0.09
    POSITIVE LOGITS
     =
    0.18
    .PerformLayout
    0.14
    .set
    0.14
     +=
    0.11
    _setopt
    0.11
    .add
    0.11
     add
    0.10
     set
    0.10
    .createFrom
    0.10
     setattr
    0.10
    Activations Density 0.021%

    No Known Activations