© 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. 24369
    Prev
    Next
    INDEX
    Explanations

    скажи, кончай

    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
    ila
    -0.10
     Aub
    -0.10
     Fore
    -0.10
     Pest
    -0.09
     ass
    -0.09
    ÑĢива
    -0.09
    ik
    -0.09
    ouden
    -0.09
    -al
    -0.09
    ving
    -0.09
    POSITIVE LOGITS
    âĦĸâĦĸ
    0.10
    abox
    0.10
    าศ
    0.10
    repos
    0.09
     Äijáo
    0.09
    -badge
    0.09
    eview
    0.09
     eoq
    0.09
     Routine
    0.09
    arbon
    0.09
    Activations Density 0.049%

    No Known Activations