© 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. 46662
    Prev
    Next
    INDEX
    Explanations

    closing brackets

    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
    anko
    -0.09
    loth
    -0.09
     stalled
    -0.08
     passe
    -0.08
     Edgar
    -0.08
     "('
    -0.08
     Kiss
    -0.08
    ynam
    -0.08
    flt
    -0.08
    =__
    -0.08
    POSITIVE LOGITS
     closing
    0.31
     Closing
    0.24
    closing
    0.23
    Closing
    0.23
     opening
    0.18
    éĹŃ
    0.18
     closes
    0.17
    éĸī
    0.17
     end
    0.14
    ç»ĵæĿŁ
    0.14
    Activations Density 0.067%

    No Known Activations