© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18640
    Prev
    Next
    INDEX
    Explanations

    Russian word fragments

    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
    Negative Logits
    оÑĤÑĮ
    -0.13
    озÑı
    -0.12
    veh
    -0.10
    ocratic
    -0.09
    ermen
    -0.09
    ÙĪاء
    -0.09
    iá»ĩt
    -0.09
    ÑĢогÑĢа
    -0.08
     srp
    -0.08
    ashi
    -0.08
    POSITIVE LOGITS
     unb
    0.09
     stout
    0.09
    utory
    0.09
    λια
    0.09
     Harley
    0.09
    ldb
    0.09
    ccoli
    0.09
     worse
    0.09
    а
    0.09
     Demp
    0.09
    Activations Density 0.023%

    No Known Activations