© 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. 24060
    Prev
    Next
    INDEX
    Explanations

    of the highest quality

    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
    ä¸ĢäºĽ
    -0.19
    ä¸Ģç§į
    -0.17
    ä¸Ģ
    -0.14
    ä¸ĢçĤ¹
    -0.13
    ä¸ĢåĢĭ
    -0.12
    ,,,,
    -0.10
    ä¸Ģå®ļ
    -0.10
    ihar
    -0.10
    aker
    -0.10
    /of
    -0.09
    POSITIVE LOGITS
    lox
    0.13
     course
    0.13
    ften
    0.13
    ffer
    0.12
    ter
    0.11
     highest
    0.11
    icers
    0.11
    tern
    0.11
    ï
    0.11
     quality
    0.10
    Activations Density 0.022%

    No Known Activations