© 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. 17551
    Prev
    Next
    INDEX
    Explanations

    price range, tax bracket, every life, which case

    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
     Shelf
    -0.15
     shelf
    -0.14
     shelves
    -0.14
    shelf
    -0.14
     sides
    -0.13
     ÙģÙī
    -0.12
     campuses
    -0.11
     occasion
    -0.11
     occasions
    -0.10
    occasion
    -0.10
    POSITIVE LOGITS
     manner
    0.19
     fashion
    0.14
     capacity
    0.13
     direction
    0.13
     stakes
    0.12
     stead
    0.12
     location
    0.12
     footsteps
    0.11
     entirety
    0.11
     locations
    0.11
    Activations Density 0.292%

    No Known Activations