© 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. 27282
    Prev
    Next
    INDEX
    Explanations

    miracle

    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
    ãĢĥ
    -0.12
     heavenly
    -0.10
    amba
    -0.10
    mtree
    -0.09
    åļ
    -0.09
    dej
    -0.09
     riches
    -0.08
    èĶµ
    -0.08
    ardo
    -0.08
     Alphabet
    -0.08
    POSITIVE LOGITS
    mir
    0.40
     miracle
    0.35
    Mir
    0.34
     Mir
    0.34
     Miracle
    0.32
     miracles
    0.29
     mir
    0.28
     záz
    0.26
     ÑĩÑĥд
    0.23
     magic
    0.21
    Activations Density 0.053%

    No Known Activations