© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 9787
    Prev
    Next
    INDEX
    Explanations

    Quark oder Curd, mozzarella

    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
    .MenuItem
    -0.10
    Soup
    -0.10
    CEF
    -0.10
    ÑĢой
    -0.10
    bac
    -0.09
    erin
    -0.09
     Metallic
    -0.09
     Chow
    -0.09
     Institution
    -0.09
    reu
    -0.09
    POSITIVE LOGITS
     cheese
    0.34
     Cheese
    0.28
    zzarella
    0.25
     cream
    0.24
     cheeses
    0.22
    che
    0.22
    eddar
    0.20
     cottage
    0.20
     mo
    0.19
     ric
    0.18
    Activations Density 0.050%

    No Known Activations