Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65525
    Prev
    Next
    INDEX
    Explanations

    math and jokes

    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
     equival
    -0.09
    kaar
    -0.09
     conspir
    -0.09
    še
    -0.09
     Spell
    -0.09
    ä¸Ī
    -0.08
     Thesis
    -0.08
    _manual
    -0.08
    assis
    -0.08
    ç¯ĩ
    -0.08
    POSITIVE LOGITS
    æķ°åѦ
    0.22
     math
    0.22
    math
    0.21
     Math
    0.21
    .math
    0.20
    Math
    0.19
     маÑĤемаÑĤи
    0.19
    (math
    0.17
     اÙĦرÙĬاض
    0.17
     mathematics
    0.17
    Activations Density 0.246%

    No Known Activations