© 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. 47410
    Prev
    Next
    INDEX
    Explanations

    purpose or reasons

    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
     Bach
    -0.09
    achen
    -0.09
    unic
    -0.09
    680
    -0.09
    451
    -0.08
    884
    -0.08
    /run
    -0.08
    loff
    -0.08
    lest
    -0.08
    opr
    -0.08
    POSITIVE LOGITS
     purposes
    0.91
     sake
    0.57
     purpose
    0.54
     PURPOSE
    0.47
     reasons
    0.46
    purpose
    0.41
    Purpose
    0.40
     Purpose
    0.39
    缮çļĦ
    0.38
     Reasons
    0.32
    Activations Density 0.135%

    No Known Activations