© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    roof and tejado

    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
     flooring
    -0.12
     Rug
    -0.11
    awah
    -0.11
     curtains
    -0.10
     ë²½
    -0.09
     floor
    -0.09
     rugs
    -0.09
    åľ°ä¸ĭ
    -0.09
     floors
    -0.09
     Flooring
    -0.09
    POSITIVE LOGITS
     roof
    0.37
     Roof
    0.32
    roof
    0.28
     roofs
    0.28
     roofing
    0.26
     rooftop
    0.24
    Ro
    0.22
     Roo
    0.21
     rooft
    0.21
    -ro
    0.20
    Activations Density 0.051%

    No Known Activations