© 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. 12472
    Prev
    Next
    INDEX
    Explanations

    sit and observe

    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
    istr
    -0.10
     cure
    -0.09
    lix
    -0.09
    engu
    -0.09
     circum
    -0.09
    oplevel
    -0.08
     im
    -0.08
    èĸĦ
    -0.08
    uent
    -0.08
     incom
    -0.08
    POSITIVE LOGITS
     sit
    0.33
     sitting
    0.27
     sits
    0.26
    sit
    0.24
    åĿIJ
    0.22
     Sit
    0.21
     Ñģид
    0.21
    Sit
    0.21
     ngá»ĵi
    0.19
     id
    0.19
    Activations Density 0.043%

    No Known Activations