© 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. 46419
    Prev
    Next
    INDEX
    Explanations

    types of things

    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
    çļĦä¸Ģ个
    -0.09
    tainment
    -0.09
    Ä°ng
    -0.08
    wdx
    -0.08
    ë²Ħì§Ģ
    -0.08
    edly
    -0.08
    stime
    -0.08
    ãĢĢãĢĢ ãĢĢ ãĢĢ ãĢĢ
    -0.08
    oldt
    -0.08
    fcn
    -0.08
    POSITIVE LOGITS
    åĪĻ
    0.13
     meanwhile
    0.11
    åīĩ
    0.11
     refers
    0.09
     ise
    0.09
     pedig
    0.09
     simply
    0.09
     section
    0.09
     zase
    0.08
    ëŀĢ
    0.08
    Activations Density 0.088%

    No Known Activations