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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44904
    Prev
    Next
    INDEX
    Explanations

    commands that instruct or tell

    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
     Vit
    -0.10
     vit
    -0.10
     plac
    -0.09
    šov
    -0.09
     insensitive
    -0.09
     
    -0.09
     rods
    -0.09
     due
    -0.08
    aya
    -0.08
    åĽ£
    -0.08
    POSITIVE LOGITS
     telling
    0.18
     instruct
    0.15
    æĦıæĢĿ
    0.15
    åijĬè¯ī
    0.14
     tell
    0.14
     saying
    0.14
     tells
    0.14
     means
    0.13
     sẽ
    0.12
     Tell
    0.12
    Activations Density 0.072%

    No Known Activations