© 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. 16932
    Prev
    Next
    INDEX
    Explanations

    air force terms

    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
     helicopters
    -0.11
    ä¿
    -0.11
     helicopter
    -0.10
     Sans
    -0.09
    929
    -0.09
    landers
    -0.09
     Helm
    -0.09
    çŁ
    -0.09
    co
    -0.08
     Param
    -0.08
    POSITIVE LOGITS
     Air
    0.23
    Air
    0.18
    afb
    0.17
     AF
    0.16
    AF
    0.16
     USA
    0.15
     air
    0.15
    .AF
    0.14
     McConnell
    0.14
     Base
    0.14
    Activations Density 0.042%

    No Known Activations