© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 59518
    Prev
    Next
    INDEX
    Explanations

    war and sacrifice

    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
     Brig
    -0.13
     Milit
    -0.12
     Squadron
    -0.12
     cavalry
    -0.11
     wartime
    -0.11
     Garrison
    -0.11
     RAF
    -0.11
     SWAT
    -0.11
     martial
    -0.11
     brig
    -0.10
    POSITIVE LOGITS
    士
    0.15
    sold
    0.15
     trench
    0.14
     Private
    0.14
     battle
    0.14
     priv
    0.14
     shell
    0.13
     solder
    0.13
     war
    0.13
     conflict
    0.13
    Activations Density 0.094%

    No Known Activations