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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34328
    Prev
    Next
    INDEX
    Explanations

    large numbers and ranges

    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
     dozens
    -0.15
     dozen
    -0.13
     infinitely
    -0.10
    è²´
    -0.10
     Hundreds
    -0.10
     Huck
    -0.10
    äºĮäºĮ
    -0.09
     thang
    -0.09
     hundreds
    -0.09
    emies
    -0.09
    POSITIVE LOGITS
     trillion
    0.13
     goog
    0.12
    illion
    0.12
    æº
    0.12
    illions
    0.12
    亿
    0.11
     large
    0.11
     gig
    0.11
     Large
    0.11
    .BigInteger
    0.11
    Activations Density 0.105%

    No Known Activations