© 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. 38891
    Prev
    Next
    INDEX
    Explanations

    parentheses balancing deepness

    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
     boxed
    -0.10
     pinned
    -0.09
    UGE
    -0.09
     Anchor
    -0.09
    iat
    -0.09
    éŀ
    -0.09
     Stam
    -0.09
     Buzz
    -0.08
    __,__
    -0.08
    coration
    -0.08
    POSITIVE LOGITS
     closing
    0.21
     opening
    0.19
     "("
    0.17
     unc
    0.17
     balance
    0.16
     Closing
    0.16
     '('
    0.16
     pare
    0.15
     Opening
    0.15
    æĭ¬
    0.15
    Activations Density 0.069%

    No Known Activations