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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 13725
    Prev
    Next
    INDEX
    Explanations

    function opening brace

    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
    _unset
    -0.10
     ({
    -0.09
    ork
    -0.09
     prov
    -0.09
     Roe
    -0.09
    atch
    -0.09
     Maiden
    -0.09
    uly
    -0.09
    //\n\n\n
    -0.09
    (
    -0.09
    POSITIVE LOGITS
     {\n
    0.19
     {\n\n
    0.12
     {č\n
    0.12
    aign
    0.11
    '){\n
    0.10
    ":{\n
    0.10
    {\n
    0.10
     AppleWebKit
    0.10
    "){\n
    0.10
    omm
    0.09
    Activations Density 0.028%

    No Known Activations