© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18816
    Prev
    Next
    INDEX
    Explanations

    building construction materials

    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
    Negative Logits
     premises
    -0.11
     åĪ¶
    -0.10
     vessels
    -0.10
     wax
    -0.09
     atmos
    -0.09
     setups
    -0.09
     Yard
    -0.09
     ï¾ļ
    -0.09
    RuntimeObject
    -0.08
    秣
    -0.08
    POSITIVE LOGITS
     building
    0.41
     Building
    0.37
    Building
    0.34
     construction
    0.33
     ÑģÑĤÑĢоиÑĤелÑĮ
    0.30
    building
    0.29
     Construction
    0.28
     xây
    0.25
    Construction
    0.25
     BUILD
    0.25
    Activations Density 0.166%

    No Known Activations