© 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. 1752
    Prev
    Next
    INDEX
    Explanations

    decision and action

    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
     conventional
    -0.08
    !\n\n\n\n
    -0.07
     Shall
    -0.07
    ...\n\n\n\n
    -0.07
     Works
    -0.07
    Besides
    -0.07
     entreprene
    -0.07
     shall
    -0.07
     fer
    -0.07
     Besides
    -0.07
    POSITIVE LOGITS
    kova
    0.08
    à¸Ńà¸Ń
    0.08
     Güven
    0.08
    abbo
    0.08
    æĽ´åĬł
    0.08
    hangi
    0.08
     Huffman
    0.08
    .sendStatus
    0.08
     обÑĢазом
    0.07
     oneself
    0.07
    Activations Density 1.067%

    No Known Activations