© 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. 50671
    Prev
    Next
    INDEX
    Explanations

    sitting and leaning

    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
    ç«Ļåľ¨
    -0.22
     standing
    -0.22
     Standing
    -0.20
    Standing
    -0.20
     steps
    -0.17
     stepped
    -0.16
     Steps
    -0.15
     stepping
    -0.14
    æŃ¥
    -0.14
     step
    -0.14
    POSITIVE LOGITS
     lean
    0.25
     Lean
    0.20
    lean
    0.20
     leaned
    0.20
     leans
    0.19
    Lean
    0.19
     sitting
    0.18
     sco
    0.18
     recl
    0.18
     leaning
    0.17
    Activations Density 0.030%

    No Known Activations