© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14
    Prev
    Next
    INDEX
    Explanations

    verbs of action after 'to'

    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
     use
    -0.15
    çĶ¨
    -0.13
     dùng
    -0.12
     gebruik
    -0.11
     usar
    -0.11
    andon
    -0.11
     kullanı
    -0.11
    \tuse
    -0.10
     Use
    -0.10
    çĶ¨çļĦ
    -0.10
    POSITIVE LOGITS
     advantage
    0.14
     maximum
    0.13
     fullest
    0.13
     Advantage
    0.11
    /from
    0.11
     Alto
    0.10
     fuel
    0.10
     full
    0.10
    fuel
    0.10
     great
    0.10
    Activations Density 0.068%

    No Known Activations