© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39000
    Prev
    Next
    INDEX
    Explanations

    installation status

    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
    unately
    -0.09
     Masters
    -0.09
     eve
    -0.08
     Kathryn
    -0.08
    à¹ģà¸ķ
    -0.08
    flux
    -0.08
    olan
    -0.08
    oola
    -0.08
     Wy
    -0.08
    ï¼Įå°±æĺ¯
    -0.08
    POSITIVE LOGITS
    æīįèĥ½
    0.20
     somewhere
    0.16
    æīį
    0.15
     otherwise
    0.15
     correctly
    0.13
    ä¸Ķ
    0.13
    otherwise
    0.12
     Otherwise
    0.12
    åIJ¦
    0.11
     correctamente
    0.11
    Activations Density 0.059%

    No Known Activations