© 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. 13274
    Prev
    Next
    INDEX
    Explanations

    person named

    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
     dub
    -0.09
    :::|
    -0.09
     dubbed
    -0.08
     Title
    -0.08
     noop
    -0.08
     âĶ
    -0.08
    ẩu
    -0.08
    orer
    -0.08
    /tiny
    -0.08
    208
    -0.08
    POSITIVE LOGITS
     named
    0.72
    named
    0.55
     Named
    0.50
    Named
    0.45
     name
    0.40
    åIJį
    0.37
    .named
    0.36
    _named
    0.35
     names
    0.32
     tên
    0.32
    Activations Density 0.239%

    No Known Activations