© 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. 24820
    Prev
    Next
    INDEX
    Explanations

    impact exercises vs

    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
     stylist
    -0.12
     knees
    -0.09
     coverage
    -0.09
     fixed
    -0.09
     jog
    -0.09
    utsch
    -0.08
    -fixed
    -0.08
     Pon
    -0.08
     tact
    -0.08
     GW
    -0.08
    POSITIVE LOGITS
     exercises
    0.26
    ercises
    0.23
     Exercises
    0.18
     Stre
    0.17
    stre
    0.16
     movements
    0.14
     Pil
    0.14
     exercise
    0.14
     warm
    0.13
     activities
    0.13
    Activations Density 0.083%

    No Known Activations