© 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. 58196
    Prev
    Next
    INDEX
    Explanations

    distinguishing from others

    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
     itself
    -0.10
    ether
    -0.10
    ãģĨãģ¡
    -0.09
    604
    -0.09
    ë¨
    -0.09
    Dia
    -0.08
     nbytes
    -0.08
    _ctx
    -0.08
    genes
    -0.08
    588
    -0.08
    POSITIVE LOGITS
     available
    0.15
     like
    0.12
    available
    0.11
     Available
    0.11
     such
    0.10
    ä¸Ģæł·
    0.10
    éĤ£æł·
    0.10
     counterparts
    0.10
     ÙħØ«ÙĦ
    0.10
     combined
    0.09
    Activations Density 0.071%

    No Known Activations