© 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. 58668
    Prev
    Next
    INDEX
    Explanations

    old Soviet-designed tanks

    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
    -0.12
     Bom
    -0.12
     bomber
    -0.11
     bombing
    -0.11
     bombers
    -0.11
    bomb
    -0.11
     bombs
    -0.11
     militar
    -0.10
     Milit
    -0.10
    weapon
    -0.10
    POSITIVE LOGITS
     tank
    0.34
     tanks
    0.29
     Tank
    0.27
    -tank
    0.24
    Tank
    0.24
     Tanks
    0.24
     Abrams
    0.22
    tank
    0.22
    åĿ¦
    0.22
     ÑĤан
    0.20
    Activations Density 0.030%

    No Known Activations