© 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. 62011
    Prev
    Next
    INDEX
    Explanations

    many, most, almost, every

    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
     EITHER
    -0.11
    äºĽ
    -0.10
     Everyday
    -0.10
     practical
    -0.10
    ä¸ĢçĤ¹
    -0.10
    à¸ļาà¸ĩ
    -0.09
     Neither
    -0.09
     nÄĽkteré
    -0.09
     некоÑĤоÑĢ
    -0.09
     Certain
    -0.08
    POSITIVE LOGITS
     almost
    0.44
    åĩłä¹İ
    0.36
     every
    0.34
     nearly
    0.34
    almost
    0.34
    Almost
    0.28
     many
    0.28
     Almost
    0.28
     pretty
    0.27
     most
    0.27
    Activations Density 0.265%

    No Known Activations