© 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. 25596
    Prev
    Next
    INDEX
    Explanations

    glimpse, peek, catch

    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
     Recap
    -0.10
    anz
    -0.09
     Hanson
    -0.09
    ayah
    -0.09
     bumps
    -0.09
    LOAT
    -0.09
    egra
    -0.08
     Outreach
    -0.08
    ReadWrite
    -0.08
     found
    -0.08
    POSITIVE LOGITS
     glimpse
    0.36
     sneak
    0.22
     insight
    0.22
     glimps
    0.22
    é¢Ħè§Ī
    0.21
     peek
    0.21
     preview
    0.21
     catch
    0.21
    impse
    0.21
     pe
    0.20
    Activations Density 0.070%

    No Known Activations