© 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. 49437
    Prev
    Next
    INDEX
    Explanations

    stumbled and fell, slippery, trip

    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
     fence
    -0.12
     fences
    -0.11
     Fence
    -0.11
    ugi
    -0.10
    æ¯Ľ
    -0.10
     relic
    -0.10
    adesh
    -0.10
     brushes
    -0.09
     sinking
    -0.09
     paddle
    -0.09
    POSITIVE LOGITS
     tri
    0.24
     slippery
    0.22
     Slip
    0.22
     slip
    0.21
     trip
    0.19
     slick
    0.18
     Trip
    0.18
     slips
    0.18
     поÑģк
    0.18
     Tri
    0.17
    Activations Density 0.020%

    No Known Activations