© 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. 60652
    Prev
    Next
    INDEX
    Explanations

    restaurant reviews and ratings

    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
     snack
    -0.12
     Cafe
    -0.10
     caf
    -0.10
     cafes
    -0.10
     cafe
    -0.10
     inv
    -0.10
     snacks
    -0.10
     Café
    -0.10
     thirst
    -0.10
     café
    -0.09
    POSITIVE LOGITS
     Yelp
    0.20
     Zag
    0.17
     reviews
    0.16
     Mich
    0.14
     recommendations
    0.14
     zag
    0.13
     reservation
    0.13
    èIJ¥ä¸ļ
    0.13
     restr
    0.12
     delivery
    0.12
    Activations Density 0.138%

    No Known Activations