© 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. 13017
    Prev
    Next
    INDEX
    Explanations

    sushi ingredients like avocado

    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
    ardu
    -0.11
     Bronze
    -0.10
    ãĥ³ãĥij
    -0.09
     Shib
    -0.09
     Burnett
    -0.09
    idian
    -0.09
     Lama
    -0.09
     é¹
    -0.09
     BSP
    -0.09
     Spit
    -0.09
    POSITIVE LOGITS
     nig
    0.20
     sushi
    0.19
     rolls
    0.18
     raw
    0.18
     Conveyor
    0.17
    寿
    0.16
     conveyor
    0.16
     roll
    0.16
     Raw
    0.15
     Roll
    0.15
    Activations Density 0.029%

    No Known Activations