© 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. 55048
    Prev
    Next
    INDEX
    Explanations

    acronyms and enumerations

    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
    .scalablytyped
    -0.12
     unint
    -0.09
    zilla
    -0.09
    /n
    -0.08
    ONGL
    -0.08
     ï¼
    -0.08
     Wilkinson
    -0.08
    æĺ¯ä¸į
    -0.08
    izu
    -0.08
     unn
    -0.08
    POSITIVE LOGITS
    éli
    0.09
    FS
    0.09
    <typeof
    0.09
    roman
    0.08
    .foundation
    0.08
    ptron
    0.08
    /Runtime
    0.08
    ML
    0.08
    borg
    0.08
    ernel
    0.08
    Activations Density 0.213%

    No Known Activations