© 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. 35820
    Prev
    Next
    INDEX
    Explanations

    removing old tags

    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
    ï¼ĮåĽł
    -0.10
    ys
    -0.09
     nữa
    -0.09
    ãĥ«ãĤ¯
    -0.08
    386
    -0.08
    ocket
    -0.08
    conde
    -0.08
    ï¼ĮåĽłä¸º
    -0.08
     Gould
    -0.08
    indsight
    -0.08
    POSITIVE LOGITS
    ï¼ĮèĢĮ
    0.32
     iar
    0.31
     èĢĮ
    0.23
     while
    0.22
     còn
    0.21
    èĢĮ
    0.21
     Ø£Ùħا
    0.20
     Meanwhile
    0.20
     zatÃŃmco
    0.20
    while
    0.19
    Activations Density 0.302%

    No Known Activations