© 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. 60904
    Prev
    Next
    INDEX
    Explanations

    sealing, waterproofing, roof restoration

    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
    edd
    -0.10
    amel
    -0.10
     perfor
    -0.10
    ä¸Ī
    -0.09
     glue
    -0.09
    inka
    -0.09
     pinned
    -0.09
     ï½
    -0.09
     dro
    -0.08
     mesh
    -0.08
    POSITIVE LOGITS
     seal
    0.25
     seals
    0.20
     Seal
    0.19
     sealing
    0.18
     Caul
    0.15
     leak
    0.15
     ca
    0.14
     Se
    0.14
    æ¼ı
    0.14
     caul
    0.14
    Activations Density 0.033%

    No Known Activations