© 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. 43806
    Prev
    Next
    INDEX
    Explanations

    list of numbers and closing brackets

    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
    :
    -0.09
    minster
    -0.09
    ator
    -0.09
     Noble
    -0.09
    ct
    -0.08
     Vend
    -0.08
    l
    -0.08
     crt
    -0.08
    2
    -0.08
    ()
    -0.08
    POSITIVE LOGITS
     omas
    0.10
    ï¼¼:
    0.08
     bald
    0.08
     localVar
    0.08
    uju
    0.08
    .mousePosition
    0.08
    okus
    0.08
    ,www
    0.08
     runApp
    0.08
    bject
    0.08
    Activations Density 0.045%

    No Known Activations