© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1576
    Prev
    Next
    INDEX
    Explanations

    Russian preposition "na" followed by noun

    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
     riv
    -0.10
     armor
    -0.09
     Roman
    -0.09
     crud
    -0.09
    /renderer
    -0.09
     ey
    -0.09
    tiv
    -0.09
     logging
    -0.08
     chalk
    -0.08
     sou
    -0.08
    POSITIVE LOGITS
    çĪ
    0.12
     gamb
    0.11
     ÑĤан
    0.11
     dolaÅŁ
    0.10
    èµ°
    0.10
    è·³
    0.10
    æŃĮ
    0.10
    è¼ī
    0.10
     Ñģка
    0.10
     tr
    0.10
    Activations Density 0.227%

    No Known Activations