© 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. 44219
    Prev
    Next
    INDEX
    Explanations

    the european

    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
     Beaver
    -0.11
     borrowing
    -0.10
     borrow
    -0.10
     consolid
    -0.09
     borrowers
    -0.09
     Stub
    -0.09
     dissip
    -0.09
    éģ£
    -0.09
     درآÙħد
    -0.09
    CLK
    -0.09
    POSITIVE LOGITS
     synd
    0.19
     Synd
    0.16
    èŀį
    0.14
     arr
    0.14
     private
    0.13
     funding
    0.13
     financing
    0.13
     EIF
    0.12
     Islamic
    0.12
    fin
    0.12
    Activations Density 0.072%

    No Known Activations