© 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. 24674
    Prev
    Next
    INDEX
    Explanations

    assistant start header

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

    the special chat-formatting marker that begins an assistant header/turn.

    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
    à¹ģà¸ģ
    -0.08
    丶
    -0.08
     nack
    -0.08
    wahl
    -0.08
    ublic
    -0.08
    ocator
    -0.07
    377
    -0.07
    ilter
    -0.07
     Joel
    -0.07
    oter
    -0.07
    POSITIVE LOGITS
     AI
    0.17
    AI
    0.14
     chat
    0.14
     Chat
    0.14
    Chat
    0.12
    _chat
    0.11
    chat
    0.11
    .ai
    0.11
    (Chat
    0.11
     gener
    0.10
    Activations Density 0.610%

    No Known Activations