© 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. 40390
    Prev
    Next
    INDEX
    Explanations

    operation, cargo, move

    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
     sailor
    -0.14
     sailors
    -0.13
     sail
    -0.11
     fus
    -0.10
     Sailor
    -0.10
     Sail
    -0.10
    ãĤĽ
    -0.10
     Sang
    -0.09
     maritime
    -0.09
     Maritime
    -0.09
    POSITIVE LOGITS
     deck
    0.12
     tween
    0.12
     SOL
    0.11
    èī
    0.11
     Deck
    0.11
     Lloyd
    0.10
     outfit
    0.10
     ke
    0.10
     subdivision
    0.10
    Deck
    0.10
    Activations Density 0.021%

    No Known Activations