© 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. 34219
    Prev
    Next
    INDEX
    Explanations

    boats with navigation and motors

    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
     sailing
    -0.12
     fleets
    -0.11
     sailed
    -0.11
     wre
    -0.11
     Sachs
    -0.11
     docks
    -0.11
     fleet
    -0.10
     cru
    -0.10
     Sailor
    -0.10
     Squad
    -0.10
    POSITIVE LOGITS
     deck
    0.36
     Deck
    0.33
    Deck
    0.28
    deck
    0.27
     decks
    0.27
    çĶ²
    0.24
    _deck
    0.21
    .deck
    0.20
    (deck
    0.19
     crew
    0.18
    Activations Density 0.032%

    No Known Activations