© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 20617
    Prev
    Next
    INDEX
    Explanations

    NumPy, Python, or HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that signal instructional or technical/documentation context, such as introducing examples, metadata, or step-by-step guidance.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    r
    -0.12
    l
    -0.11
    .printStackTrace
    -0.11
    m
    -0.10
    k
    -0.10
    e
    -0.10
    -0.10
    T
    -0.10
    325
    -0.09
    h
    -0.09
    POSITIVE LOGITS
    >NN
    0.12
    .scalablytyped
    0.11
     огÑĢа
    0.10
    actionDate
    0.10
    Intialized
    0.10
    Gratis
    0.10
    urette
    0.10
     пÑĢоÑĦеÑģÑģионалÑĮ
    0.09
    INVAL
    0.09
    ););\n
    0.09
    Activations Density 0.021%

    No Known Activations