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. 65409
    Prev
    Next
    INDEX
    Explanations

    following command sudo

    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
     Windows
    -0.10
    Ĺ
    -0.10
     GX
    -0.10
     Entr
    -0.09
     Rip
    -0.09
     tir
    -0.09
    _cpu
    -0.09
     HEAD
    -0.09
     Shepherd
    -0.09
     windows
    -0.09
    POSITIVE LOGITS
    sudo
    0.17
     sudo
    0.17
     sud
    0.13
     cat
    0.12
     touch
    0.12
    cat
    0.11
     editor
    0.11
     nano
    0.11
    ovi
    0.11
    aticon
    0.11
    Activations Density 0.071%

    No Known Activations