© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13762
    Prev
    Next
    INDEX
    Explanations

    foreign languages and symbols

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

    text that appears non-English or uses non-ASCII characters (foreign scripts, diacritics, or Greek letters), signaling multilingual content.

    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
    ebek
    -0.08
    /cards
    -0.07
    èo
    -0.07
    orget
    -0.07
    =======\n
    -0.07
     buttonText
    -0.07
    seealso
    -0.06
    pictured
    -0.06
    lluminate
    -0.06
    lectic
    -0.06
    POSITIVE LOGITS
    .RightToLeft
    0.08
    âĢħ
    0.08
    biên
    0.08
    groupBox
    0.08
    0.07
    Âłmiles
    0.07
    printStats
    0.07
    /******/
    0.06
    *,
    0.06
    наÑģлÑĸдок
    0.06
    Activations Density 4.760%

    No Known Activations