© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35289
    Prev
    Next
    INDEX
    Explanations

    detects '()' at end of strings

    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
     fkk
    -0.11
    {}",
    -0.11
    ocha
    -0.09
    \\"
    -0.09
    orent
    -0.09
    {}]
    -0.09
     ÄĮech
    -0.09
    .::
    -0.09
     "-//
    -0.09
     nuru
    -0.09
    POSITIVE LOGITS
     Kirk
    0.10
    012
    0.10
    thon
    0.10
     Kong
    0.10
    X
    0.09
    M
    0.08
     Mich
    0.08
    E
    0.08
    x
    0.08
     Pyongyang
    0.08
    Activations Density 0.072%

    No Known Activations