© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21823
    Prev
    Next
    INDEX
    Explanations

    simple wave or complex design

    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
     sailed
    -0.12
     sails
    -0.12
     sail
    -0.12
     Yosemite
    -0.10
     shoreline
    -0.10
     Sail
    -0.10
     sailing
    -0.10
     Roma
    -0.09
     wildfire
    -0.09
     Panda
    -0.09
    POSITIVE LOGITS
     mer
    0.25
     Mer
    0.18
     sea
    0.17
     Pose
    0.17
     Atl
    0.17
     wave
    0.17
     water
    0.16
     Levi
    0.15
     waves
    0.15
     blue
    0.14
    Activations Density 0.135%

    No Known Activations