© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43984
    Prev
    Next
    INDEX
    Explanations

    listing fitness activities

    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
     athletic
    -0.16
     workout
    -0.14
     Athletic
    -0.13
     jogging
    -0.12
     Workout
    -0.11
     Athletics
    -0.11
     sporting
    -0.11
     sweat
    -0.10
     athletes
    -0.10
     Sporting
    -0.10
    POSITIVE LOGITS
     row
    0.17
     pil
    0.17
     Pil
    0.16
     Cross
    0.15
     kick
    0.14
     pole
    0.14
     running
    0.14
     weights
    0.13
     strength
    0.13
    pole
    0.13
    Activations Density 0.079%

    No Known Activations