© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1235
    Prev
    Next
    INDEX
    Explanations

    fail to

    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
    wik
    -0.10
    969
    -0.09
    orrow
    -0.09
    wij
    -0.09
    湯
    -0.09
    ventus
    -0.09
    -taking
    -0.09
     bol
    -0.09
    OutOfRangeException
    -0.09
    CodeGen
    -0.08
    POSITIVE LOGITS
    ures
    0.18
    ture
    0.14
    over
    0.14
    URES
    0.13
    afe
    0.12
     fail
    0.12
     Bren
    0.12
    ingly
    0.12
    .Failure
    0.12
    .Fail
    0.12
    Activations Density 0.025%

    No Known Activations