© 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. 27395
    Prev
    Next
    INDEX
    Explanations

    only followed by limited condition

    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
     Zucker
    -0.10
    sti
    -0.09
    åıªæĺ¯
    -0.09
    yme
    -0.09
    ĥģ
    -0.09
    elli
    -0.09
    ù
    -0.09
    shed
    -0.09
     Äijã
    -0.09
    }->{
    -0.09
    POSITIVE LOGITS
     лиÑĪÑĮ
    0.21
     ever
    0.21
    fans
    0.16
    ever
    0.15
    ä¸įè¿ĩ
    0.14
    -ever
    0.13
    Fans
    0.13
     margin
    0.12
     truly
    0.12
     recently
    0.12
    Activations Density 0.038%

    No Known Activations