© 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. 38985
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters

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

    very short tokens, especially common function words, punctuation, and compact formatted elements like date/time or identifier fragments.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    tring
    -0.08
    annie
    -0.08
     pione
    -0.08
     sole
    -0.08
    ichert
    -0.07
     ฿
    -0.07
    /=
    -0.07
    WebElement
    -0.07
    seconds
    -0.07
    ibrated
    -0.07
    POSITIVE LOGITS
     Rah
    0.08
    彡
    0.08
    عÙĦÙĪÙħات
    0.07
     neod
    0.07
    Disposable
    0.07
    CATEGORY
    0.07
     Zur
    0.07
    boxing
    0.07
    nÃŃk
    0.07
    uyá»ĩn
    0.07
    Activations Density 0.341%

    No Known Activations