© 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. 24560
    Prev
    Next
    INDEX
    Explanations

    Italian desserts

    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
    PPER
    -0.09
     chocolates
    -0.09
     beers
    -0.09
     Pep
    -0.09
     champagne
    -0.09
     pepper
    -0.09
     Soda
    -0.09
     Champagne
    -0.09
     bouquet
    -0.09
     Curl
    -0.09
    POSITIVE LOGITS
     desert
    0.26
     cust
    0.24
     dessert
    0.23
     tir
    0.22
     pie
    0.21
     Cust
    0.21
    dess
    0.20
     Desert
    0.19
     chees
    0.19
    cust
    0.19
    Activations Density 0.074%

    No Known Activations