© 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. 39255
    Prev
    Next
    INDEX
    Explanations

    preposition followed by adjective/noun

    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
    çļĦä¸Ģ个
    -0.12
    ä¸Ģ个
    -0.12
    æĺ¯ä¸Ģ个
    -0.11
     an
    -0.11
    ä¸ĢåĢĭ
    -0.11
     sebuah
    -0.10
     a
    -0.10
     eine
    -0.09
    <|begin_of_text|>
    -0.09
     een
    -0.08
    POSITIVE LOGITS
    /from
    0.10
    ï¿
    0.08
     prob
    0.08
    /by
    0.08
     ÑĤакими
    0.08
    inyin
    0.07
     ÑĤакие
    0.07
    âĶ
    0.07
     searchData
    0.07
    .RELATED
    0.07
    Activations Density 0.416%

    No Known Activations