© 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. 15846
    Prev
    Next
    INDEX
    Explanations

    concept of both

    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
     latter
    -0.14
    è¿Ļ个
    -0.11
    éĤ£ä¸ª
    -0.10
    åı¦ä¸Ģ
    -0.09
    âĶĶ
    -0.09
    rou
    -0.09
    imen
    -0.08
    (Collections
    -0.08
     one
    -0.08
     ALL
    -0.08
    POSITIVE LOGITS
     both
    0.31
    both
    0.27
    两个
    0.24
    Both
    0.24
     Both
    0.24
    åĪĨåĪ«
    0.24
     beiden
    0.22
     two
    0.22
    両
    0.22
    _both
    0.21
    Activations Density 0.331%

    No Known Activations