© 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. 22689
    Prev
    Next
    INDEX
    Explanations

    crystal structure formation

    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
    iferay
    -0.10
     Decay
    -0.09
    æŀ
    -0.09
     ser
    -0.09
    rieb
    -0.09
     Pods
    -0.09
    éĻ¶
    -0.09
     coins
    -0.08
    vc
    -0.08
    ég
    -0.08
    POSITIVE LOGITS
     crystal
    0.29
     Crystal
    0.29
    Crystal
    0.28
     crystals
    0.27
    æĻ¶
    0.24
     кÑĢи
    0.21
     rec
    0.20
    CRY
    0.20
     supers
    0.20
     nucle
    0.17
    Activations Density 0.031%

    No Known Activations