© 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. 430
    Prev
    Next
    INDEX
    Explanations

    file path and code structure

    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
     STDCALL
    -0.08
    linkplain
    -0.08
     geschichten
    -0.08
    âĸį
    -0.08
    ĮĴ
    -0.08
     tavs
    -0.08
    ollectors
    -0.08
    .DEFINE
    -0.08
    ò
    -0.08
     -*-č\n
    -0.08
    POSITIVE LOGITS
     latter
    0.14
    0.11
    "
    0.08
     Uploaded
    0.07
    acier
    0.07
    对æĸ¹
    0.07
     pathMatch
    0.07
    ex
    0.06
    '
    0.06
    vironment
    0.06
    Activations Density 3.024%

    No Known Activations