© 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. 31036
    Prev
    Next
    INDEX
    Explanations

    skilled professionals and technicians

    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
     which
    -0.10
    eson
    -0.10
    ulumi
    -0.09
     ÑĢавно
    -0.09
    \xaa
    -0.09
    yll
    -0.08
    xing
    -0.08
    æĺ¯æĪij
    -0.08
    ahl
    -0.08
     Fork
    -0.08
    POSITIVE LOGITS
    æĿ¥è¯´
    0.11
    comes
    0.11
     ÙģØ¥ÙĨ
    0.11
    agen
    0.10
     comes
    0.09
    ,this
    0.09
     intact
    0.09
    anco
    0.09
    ilet
    0.09
    éħįåIJĪ
    0.09
    Activations Density 0.078%

    No Known Activations