© 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. 16878
    Prev
    Next
    INDEX
    Explanations

    saying i know

    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
     Recognition
    -0.11
     dubbed
    -0.10
     hors
    -0.10
     THINK
    -0.09
    enes
    -0.09
    .raw
    -0.09
    ión
    -0.09
    iry
    -0.09
    ayne
    -0.09
    ä¸įçŁ¥
    -0.09
    POSITIVE LOGITS
     know
    0.41
     knows
    0.36
    çŁ¥éģĵ
    0.35
     aware
    0.31
     biết
    0.29
     знаÑİ
    0.28
     Know
    0.27
    know
    0.27
    Know
    0.26
     understand
    0.25
    Activations Density 0.055%

    No Known Activations