© 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. 63736
    Prev
    Next
    INDEX
    Explanations

    materials, construction, chemical products

    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
     Materials
    -0.23
     materials
    -0.23
    Materials
    -0.19
    materials
    -0.18
    æĿIJæĸĻ
    -0.17
    æĿIJ
    -0.16
     materia
    -0.15
    /material
    -0.14
     MATERIAL
    -0.13
     material
    -0.13
    POSITIVE LOGITS
     finished
    0.17
     Finished
    0.12
     equipment
    0.12
     labor
    0.11
    Finished
    0.11
     processing
    0.11
    finished
    0.11
     labour
    0.10
     airspace
    0.10
    uste
    0.10
    Activations Density 0.052%

    No Known Activations