© 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. 27168
    Prev
    Next
    INDEX
    Explanations

    show, demonstrate, prove

    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
    opp
    -0.10
     instruct
    -0.09
     faithful
    -0.08
     confirming
    -0.08
     mari
    -0.08
     Pod
    -0.08
     discour
    -0.08
     fu
    -0.08
     Clem
    -0.08
     li
    -0.08
    POSITIVE LOGITS
     show
    0.37
     показ
    0.32
    è¯ģæĺİ
    0.31
    show
    0.31
     prove
    0.29
     demonstrate
    0.29
     доказ
    0.28
    .show
    0.28
     showed
    0.27
    Demon
    0.27
    Activations Density 0.140%

    No Known Activations