© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 44090
    Prev
    Next
    INDEX
    Explanations

    door is closed

    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
    emit
    -0.11
    yyy
    -0.10
    dlg
    -0.10
    ALCHEMY
    -0.10
    tings
    -0.09
    oid
    -0.09
    á»IJ
    -0.09
    ency
    -0.09
    æ´ģ
    -0.09
    anki
    -0.09
    POSITIVE LOGITS
    ways
    0.26
    bell
    0.24
    steps
    0.19
    frame
    0.17
    stop
    0.15
     sá»ķ
    0.15
    WAYS
    0.13
    way
    0.13
    ill
    0.13
    /window
    0.13
    Activations Density 0.020%

    No Known Activations