© 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. 37167
    Prev
    Next
    INDEX
    Explanations

    not necessarily better

    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
     quieter
    -0.11
     decent
    -0.09
     nearer
    -0.09
    ternal
    -0.09
     simpler
    -0.09
     Parkinson
    -0.08
    iren
    -0.08
     ноÑĢм
    -0.08
    ä¸
    -0.08
     Hayes
    -0.08
    POSITIVE LOGITS
     superior
    0.57
     superiority
    0.47
     Superior
    0.44
     inferior
    0.31
    æ¯Ķ
    0.29
     better
    0.28
     advantage
    0.27
    ä¼ĺåĬ¿
    0.27
     ahead
    0.25
    better
    0.24
    Activations Density 0.303%

    No Known Activations