© 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. 51962
    Prev
    Next
    INDEX
    Explanations

    continuations of phrases

    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
    éĩĬ
    -0.08
     ç¶
    -0.08
    ¥IJ
    -0.08
    ufe
    -0.08
     frees
    -0.08
    æĦ
    -0.07
     Freed
    -0.07
     bomb
    -0.07
    vail
    -0.07
     denen
    -0.07
    POSITIVE LOGITS
    ä¸įæĺ¯
    0.10
     Bite
    0.10
     wasn
    0.10
     ÙĨÛĮست
    0.10
     isn
    0.09
    ÐIJÑĢÑħÑĸв
    0.09
     नह
    0.09
     deÄŁil
    0.09
    ãģ§ãģ¯ãģªãģı
    0.08
    eturn
    0.08
    Activations Density 0.091%

    No Known Activations