© 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. 39505
    Prev
    Next
    INDEX
    Explanations

    small distributor or initially involved

    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
     newer
    -0.11
    GIS
    -0.10
     recently
    -0.10
     Laz
    -0.09
     cen
    -0.09
     Dut
    -0.09
    ovsky
    -0.09
    iv
    -0.08
     multi
    -0.08
     recent
    -0.08
    POSITIVE LOGITS
     humble
    0.24
     small
    0.20
     modest
    0.20
     simple
    0.16
    å°ı
    0.16
     неболÑĮ
    0.14
     ìŀijìĿĢ
    0.14
    small
    0.14
     неболÑĮÑĪ
    0.14
     peque
    0.14
    Activations Density 0.120%

    No Known Activations