© 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. 24535
    Prev
    Next
    INDEX
    Explanations

    assistant greeting hello

    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
    ï¾ij
    -0.09
    ymes
    -0.09
     Marino
    -0.09
    arium
    -0.08
     Jing
    -0.08
    ongyang
    -0.08
    æľīçļĦ
    -0.08
     Maar
    -0.08
    åŃIJçļĦ
    -0.08
    472
    -0.08
    POSITIVE LOGITS
     hello
    0.21
     Hello
    0.20
    Hello
    0.18
    ëħķíķĺìĦ¸ìļĶ
    0.18
    hello
    0.17
     hi
    0.16
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.15
    _hello
    0.14
    Hi
    0.14
     Hi
    0.14
    Activations Density 0.036%

    No Known Activations