© 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. 12915
    Prev
    Next
    INDEX
    Explanations

    His eyes fixed

    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
     wink
    -0.13
    æ³£
    -0.12
    -REAL
    -0.10
    sob
    -0.09
    earer
    -0.09
     ngu
    -0.09
    æı¡
    -0.09
    ogan
    -0.09
     pud
    -0.09
     Bund
    -0.09
    POSITIVE LOGITS
     crossed
    0.21
     cross
    0.17
    -cross
    0.17
     Crossing
    0.17
     crossing
    0.17
     arms
    0.16
    Cross
    0.16
    cross
    0.16
     CROSS
    0.16
     Cross
    0.16
    Activations Density 0.031%

    No Known Activations