© 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. 38974
    Prev
    Next
    INDEX
    Explanations

    because, due to, detail:

    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
     modne
    -0.11
    EMPLARY
    -0.11
    -------------</
    -0.10
    <|begin_of_text|>
    -0.10
    ¶Į
    -0.10
    ÂĢÂĢ
    -0.10
    /renderer
    -0.10
    ĮĴ
    -0.09
    ëį°ìĿ´íĬ¸
    -0.09
    ----------</
    -0.09
    POSITIVE LOGITS
     because
    0.17
    because
    0.14
    ;
    0.12
    ecause
    0.11
     поÑĤомÑĥ
    0.11
     Because
    0.10
     porque
    0.10
     karena
    0.10
    Because
    0.09
    :
    0.09
    Activations Density 0.361%

    No Known Activations