© 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. 15368
    Prev
    Next
    INDEX
    Explanations

    unexpected, unwanted, arbitrary

    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
     unreachable
    -0.12
    oba
    -0.10
     unsuccessfully
    -0.10
    Impossible
    -0.10
     inconsist
    -0.10
     Impossible
    -0.10
    chio
    -0.09
     Unable
    -0.09
     unavoid
    -0.09
    alama
    -0.09
    POSITIVE LOGITS
     unexpected
    0.31
     unwanted
    0.29
    Unexpected
    0.27
    unexpected
    0.26
     surprise
    0.24
     Unexpected
    0.23
    æĦı
    0.22
     unw
    0.19
     unauthorized
    0.19
     Surprise
    0.19
    Activations Density 0.151%

    No Known Activations