© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 42993
    Prev
    Next
    INDEX
    Explanations

    server performance thresholds

    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
     max
    -0.11
    ise
    -0.10
     Apt
    -0.09
     pr
    -0.09
     Circular
    -0.09
    457
    -0.09
    .opensource
    -0.09
     maximum
    -0.09
    bung
    -0.09
     Burr
    -0.08
    POSITIVE LOGITS
     normal
    0.23
     NORMAL
    0.20
    normal
    0.20
    Normal
    0.19
     Normal
    0.19
    æŃ£å¸¸
    0.19
    (normal
    0.17
     considered
    0.16
     Anything
    0.16
    .normal
    0.16
    Activations Density 0.064%

    No Known Activations