© 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. 44550
    Prev
    Next
    INDEX
    Explanations

    romance language suffixes

    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
    ness
    -0.11
     se
    -0.11
     اختÙĦ
    -0.10
    ly
    -0.10
    ply
    -0.10
     migrationBuilder
    -0.10
     Å¡to
    -0.10
    ä¹ĭä¸Ģ
    -0.09
    esting
    -0.09
    adesh
    -0.09
    POSITIVE LOGITS
    çļĦæĺ¯
    0.18
    ÏĦαι
    0.15
    ient
    0.15
    azÄĥ
    0.15
     itself
    0.14
    (va
    0.14
    ait
    0.13
    /is
    0.13
     Ñģобой
    0.12
    rait
    0.12
    Activations Density 0.189%

    No Known Activations