© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18621
    Prev
    Next
    INDEX
    Explanations

    file, unique, plant, download, cross, cup, copy

    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
    Negative Logits
    !\n\n\n\n\n\n
    -0.07
    ãĥ»ãĥ»ãĥ»\n\n
    -0.07
     Gerard
    -0.07
     moduleId
    -0.06
     Alumni
    -0.06
    asley
    -0.06
     nackte
    -0.06
    pects
    -0.06
    ､_
    -0.06
     Yol
    -0.06
    POSITIVE LOGITS
    ******č\n
    0.09
    .Formatter
    0.08
    ¯¼
    0.08
     \t\t\n
    0.08
    .MockMvc
    0.08
    ³Øª
    0.07
     -*-č\n
    0.07
    įng
    0.07
    ¶Į
    0.07
    ·¸
    0.07
    Activations Density 0.337%

    No Known Activations