© 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. 41581
    Prev
    Next
    INDEX
    Explanations

    its mission and activities

    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
     Organizations
    -0.13
    organizations
    -0.11
     company
    -0.11
     organizations
    -0.10
    TRGL
    -0.10
     manufacture
    -0.09
     organisations
    -0.09
    preter
    -0.09
    roker
    -0.09
     -*-č\n
    -0.09
    POSITIVE LOGITS
     mission
    0.33
     activities
    0.29
    mission
    0.25
     Mission
    0.24
     missions
    0.24
    Mission
    0.21
     operations
    0.21
    activities
    0.21
     activity
    0.21
     Activities
    0.20
    Activations Density 0.140%

    No Known Activations