© 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. 10776
    Prev
    Next
    INDEX
    Explanations

    pointer or icon after "a"

    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
     vamp
    -0.10
    getHeight
    -0.09
    ODO
    -0.08
     Tick
    -0.08
    HEIGHT
    -0.08
    надлеж
    -0.08
     normals
    -0.08
    AtIndex
    -0.08
     exp
    -0.08
     yOffset
    -0.08
    POSITIVE LOGITS
     mouse
    0.29
     Mouse
    0.23
    mouse
    0.20
     mice
    0.19
     cursor
    0.17
    Mouse
    0.17
    é¼ł
    0.17
     MOUSE
    0.16
    (mouse
    0.16
    .mouse
    0.15
    Activations Density 0.041%

    No Known Activations