© 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. 47026
    Prev
    Next
    INDEX
    Explanations

    mercenary, fighting, assigned, died

    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
     civilian
    -0.16
    競
    -0.10
     civilians
    -0.10
     wartime
    -0.09
     конкÑĥÑĢ
    -0.09
     ambitious
    -0.09
     Olymp
    -0.09
    надлеж
    -0.09
    adius
    -0.09
    ulkan
    -0.08
    POSITIVE LOGITS
     fight
    0.30
     fought
    0.30
     fighting
    0.27
     fights
    0.26
    fight
    0.25
     Fight
    0.20
    åıĤåĬł
    0.18
    Fight
    0.18
     ìĭ¸
    0.18
     campaigns
    0.18
    Activations Density 0.071%

    No Known Activations