© 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. 37674
    Prev
    Next
    INDEX
    Explanations

    fake words and nonsense

    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
     cocks
    -0.10
    uard
    -0.09
     Dia
    -0.09
    ãĤĽ
    -0.09
    lace
    -0.09
    outu
    -0.09
     pun
    -0.08
    APON
    -0.08
     nast
    -0.08
    ulin
    -0.08
    POSITIVE LOGITS
    adoop
    0.12
    oodle
    0.12
    ums
    0.12
    ity
    0.10
    Widget
    0.10
     nonsense
    0.10
    iddle
    0.10
    adoo
    0.10
     boom
    0.10
    widget
    0.10
    Activations Density 0.111%

    No Known Activations