© 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. 39810
    Prev
    Next
    INDEX
    Explanations

    programming code and specific terms

    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
    &nbsp
    -0.12
    \n
    -0.12
    <strong
    -0.11
    "
    -0.10
    \t
    -0.10
    alysis
    -0.10
    <br
    -0.10
    ãĢįãģ¨
    -0.10
    \n
    -0.10
    /or
    -0.10
    POSITIVE LOGITS
    ï¸ı
    0.24
    ï¸
    0.14
    ÂĢÂĻ
    0.14
    amp
    0.11
    âĤ¬âĦ¢
    0.09
    éŀ
    0.09
    çļĦå°ı
    0.09
    <!--<
    0.09
    hap
    0.08
    ----------------------------------------------------------------------\n
    0.08
    Activations Density 0.094%

    No Known Activations