© 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. 41861
    Prev
    Next
    INDEX
    Explanations

    grounds property premises site

    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
     watering
    -0.11
     Apartment
    -0.10
     Apartments
    -0.10
     Pavilion
    -0.10
    pref
    -0.10
     inhabitants
    -0.10
     Room
    -0.09
     Places
    -0.09
     delic
    -0.09
    ansi
    -0.09
    POSITIVE LOGITS
     grounds
    0.39
     property
    0.38
     site
    0.37
     premises
    0.32
     campus
    0.31
    property
    0.28
     compound
    0.28
    grounds
    0.27
     Property
    0.24
    -site
    0.24
    Activations Density 0.102%

    No Known Activations