© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2264
    Prev
    Next
    INDEX
    Explanations

    module attributes and descriptors

    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
    çĶ
    -0.10
    esso
    -0.09
     equivalents
    -0.09
     ters
    -0.09
     Cookies
    -0.09
     TArray
    -0.08
     Bust
    -0.08
     Arlington
    -0.08
     Tour
    -0.08
     Pit
    -0.08
    POSITIVE LOGITS
    tul
    0.12
    descriptor
    0.10
     str
    0.09
    _descriptor
    0.09
     -*-č\n
    0.09
    ě[
    0.09
     Ulus
    0.09
    ******č\n
    0.09
    WithPath
    0.09
    <class
    0.09
    Activations Density 0.038%

    No Known Activations