© 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. 32476
    Prev
    Next
    INDEX
    Explanations

    warm-up before light cardio

    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
     workout
    -0.10
     memor
    -0.10
     Benedict
    -0.10
    _seed
    -0.09
     Workflow
    -0.09
     prog
    -0.09
     Griffith
    -0.09
     Workout
    -0.09
    çĸ²
    -0.09
     Urs
    -0.09
    POSITIVE LOGITS
     warm
    0.36
    warm
    0.29
     Warm
    0.29
     warming
    0.26
    Warm
    0.24
    æļĸ
    0.20
     warmed
    0.19
     warmer
    0.18
     warmth
    0.18
     ấm
    0.16
    Activations Density 0.029%

    No Known Activations