© 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. 35404
    Prev
    Next
    INDEX
    Explanations

    , where or which

    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
    yon
    -0.09
    *
    -0.09
     ìŀĪê³ł
    -0.09
     ÙĪÙĦÙħ
    -0.08
    °ëĭ¤
    -0.08
    âĦ¢
    -0.08
    iverz
    -0.08
    -Smith
    -0.08
     并
    -0.07
     BUT
    -0.07
    POSITIVE LOGITS
     which
    0.15
    which
    0.14
     à¸ĭ
    0.14
    ï¼Įåħ¶ä¸Ń
    0.13
     коÑĤоÑĢÑĭй
    0.12
    {},
    0.11
    .which
    0.10
    à¥Ī,
    0.10
     ìŀĪëĬĶëį°
    0.10
     коÑĤоÑĢаÑı
    0.10
    Activations Density 0.168%

    No Known Activations