© 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. 23089
    Prev
    Next
    INDEX
    Explanations

    drones have, many reasons

    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
     further
    -0.11
     overall
    -0.10
     sometimes
    -0.10
     likely
    -0.09
    overall
    -0.09
     another
    -0.09
     increasingly
    -0.09
     eventually
    -0.09
     Another
    -0.08
    âĶ¬
    -0.08
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.09
    Å¡ker
    0.09
     -*-č\n
    0.08
     kök
    0.08
    raç
    0.08
    ÐIJÑĢÑħÑĸв
    0.08
     modne
    0.08
     詳細
    0.08
     LPARAM
    0.08
     anything
    0.08
    Activations Density 0.025%

    No Known Activations