© 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. 18014
    Prev
    Next
    INDEX
    Explanations

    ãģ¡ãĤĵ

    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
    ãģĹãģªãģĦ
    -0.17
    ãĤĵãģ©
    -0.15
    ãģ¡ãģ¯
    -0.14
    ãģĻãģİ
    -0.14
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.13
    ãģĿãģĨãģª
    -0.12
    çĽijåIJ¬é¡µéĿ¢
    -0.12
    ãģ£ãģ¡
    -0.12
    ãģĮãģĬ
    -0.12
    ãģijãĤĮãģ©
    -0.12
    POSITIVE LOGITS
    ķãĤĵ
    0.13
    ãĥ¼
    0.13
     ãĤ
    0.11
    ãĥ¼ãĥ¼
    0.11
    au
    0.10
    etto
    0.10
    ãģĦ
    0.10
    ãģ¤
    0.09
    ãģĹ
    0.09
    ipp
    0.09
    Activations Density 0.069%

    No Known Activations