© 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. 22256
    Prev
    Next
    INDEX
    Explanations

    building and structure

    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
     Cemetery
    -0.10
     farms
    -0.10
     Bedroom
    -0.10
     cemetery
    -0.10
     graveyard
    -0.09
     (){
    -0.09
     Bedrooms
    -0.09
     домаÑĪ
    -0.09
     camps
    -0.09
     parks
    -0.09
    POSITIVE LOGITS
     building
    0.54
     buildings
    0.49
    building
    0.38
     Building
    0.37
    Building
    0.34
     зд
    0.33
     Buildings
    0.32
    -building
    0.29
    _building
    0.28
     structure
    0.27
    Activations Density 0.101%

    No Known Activations