© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41729
    Prev
    Next
    INDEX
    Explanations

    drivable area or Pygame

    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
     trans
    -0.11
     ãĥ¾
    -0.10
    heimer
    -0.10
    xor
    -0.10
    ForRow
    -0.10
    ObjectContext
    -0.09
     Wilde
    -0.09
     pent
    -0.09
    INU
    -0.08
     Vera
    -0.08
    POSITIVE LOGITS
     cloud
    0.13
    .colors
    0.11
    EMPLARY
    0.11
     Lid
    0.10
    <pcl
    0.10
    illac
    0.10
    lew
    0.10
     Coloring
    0.09
     clouds
    0.09
    PointCloud
    0.09
    Activations Density 0.006%

    No Known Activations