© 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. 21937
    Prev
    Next
    INDEX
    Explanations

    customer service, products, and solutions

    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
    /services
    -0.13
    -services
    -0.12
    \Services
    -0.12
    services
    -0.11
     services
    -0.11
    $MESS
    -0.11
    ãĤµãĥ¼ãĥĵãĤ¹
    -0.10
    èľĺèĽĽ
    -0.10
    _SERVICE
    -0.10
     ìĦľë¹ĦìĬ¤
    -0.10
    POSITIVE LOGITS
     products
    0.12
     product
    0.12
     support
    0.11
     satisfaction
    0.11
     Products
    0.11
    Products
    0.11
     competitive
    0.10
     Competitive
    0.10
    idot
    0.10
    Monkey
    0.10
    Activations Density 0.018%

    No Known Activations