© 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. 12055
    Prev
    Next
    INDEX
    Explanations

    low-level programming

    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
     koc
    -0.12
    Soft
    -0.09
     UNICODE
    -0.09
    à¹ģà¸ŀ
    -0.09
    soft
    -0.09
    DoubleClick
    -0.08
    oppins
    -0.08
    /autoload
    -0.08
    OfString
    -0.08
    ckett
    -0.08
    POSITIVE LOGITS
     low
    0.47
     Low
    0.37
    low
    0.36
    Low
    0.34
    ä½İ
    0.34
     низ
    0.32
     lower
    0.32
     LOW
    0.32
    -low
    0.32
     lowest
    0.31
    Activations Density 0.165%

    No Known Activations