© 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. 51404
    Prev
    Next
    INDEX
    Explanations

    which or what

    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
     Sort
    -0.14
    ãĢĥ
    -0.09
     POSSIBILITY
    -0.09
    _Lean
    -0.09
    ulings
    -0.08
    EDIA
    -0.08
     meaning
    -0.08
    actic
    -0.08
    ä¹ĭä¸Ģ
    -0.08
    ationale
    -0.08
    POSITIVE LOGITS
     which
    0.33
    åĵª
    0.31
     what
    0.30
     Which
    0.29
    Which
    0.28
     WHICH
    0.26
    which
    0.26
     how
    0.24
    what
    0.23
     welche
    0.22
    Activations Density 0.193%

    No Known Activations