© 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. 58560
    Prev
    Next
    INDEX
    Explanations

    class / object initialization

    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
    stal
    -0.10
    uluk
    -0.09
     TMPro
    -0.09
    iff
    -0.09
    itta
    -0.08
    _typeof
    -0.08
    ophon
    -0.08
    à¸ķลà¸Ńà¸Ķ
    -0.08
    /*č\n
    -0.08
     concent
    -0.08
    POSITIVE LOGITS
    (Constructor
    0.15
     constructor
    0.14
     contr
    0.13
     InitializeComponent
    0.12
     initial
    0.12
    CTOR
    0.12
     Constructor
    0.12
     arguments
    0.12
    Constructor
    0.12
    .newInstance
    0.12
    Activations Density 0.037%

    No Known Activations