© 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. 9403
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation marks that end sentences or responses, particularly periods and question marks.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     holog
    -0.09
    âĢ¦.\n\n
    -0.09
     tha
    -0.08
    å¼ĭ
    -0.08
    anuts
    -0.08
     Cra
    -0.08
    æĢ
    -0.08
     singleton
    -0.08
    /stream
    -0.08
     Locale
    -0.08
    POSITIVE LOGITS
    Intialized
    0.09
    veloper
    0.09
    jpg
    0.09
     quo
    0.08
    оÑĢг
    0.08
     Crescent
    0.08
    este
    0.08
    çĴĥ
    0.08
     tweet
    0.08
     بÙĪابة
    0.08
    Activations Density 0.058%

    No Known Activations