© 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. 54016
    Prev
    Next
    INDEX
    Explanations

    navigation and nautical 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
     Sailor
    -0.13
     Maritime
    -0.12
     beach
    -0.12
     sailors
    -0.12
     submar
    -0.11
     Beach
    -0.11
    inning
    -0.11
     Harbour
    -0.10
     mainland
    -0.10
     submarine
    -0.10
    POSITIVE LOGITS
     vessel
    0.24
     vessels
    0.22
     shipping
    0.18
     nav
    0.17
     navigation
    0.17
     AIS
    0.17
     merchant
    0.15
    -navigation
    0.15
     Navigation
    0.14
     Shipping
    0.14
    Activations Density 0.026%

    No Known Activations