© 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. 4688
    Prev
    Next
    INDEX
    Explanations

    data fields format structure

    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
     Dudley
    -0.09
    ocache
    -0.09
    utta
    -0.09
     setting
    -0.09
    SSL
    -0.09
    iode
    -0.09
    ibox
    -0.08
     words
    -0.08
    ispecies
    -0.08
     hollow
    -0.08
    POSITIVE LOGITS
     format
    0.30
    æł¼å¼ı
    0.25
     structure
    0.24
     formats
    0.24
     Format
    0.23
     Structure
    0.22
    Structure
    0.20
     formato
    0.20
    format
    0.20
    structure
    0.20
    Activations Density 0.237%

    No Known Activations