© 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. 3804
    Prev
    Next
    INDEX
    Explanations

    filter or filtering

    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
     Cycle
    -0.12
    çļ
    -0.10
     Fur
    -0.09
    fork
    -0.09
     Gott
    -0.09
     capacit
    -0.09
     Pawn
    -0.09
     Fork
    -0.09
     fork
    -0.08
     Bott
    -0.08
    POSITIVE LOGITS
     filter
    0.31
     filters
    0.25
     Butter
    0.25
     Filter
    0.24
    filter
    0.24
    Filter
    0.21
     butter
    0.20
    (filter
    0.20
     Filters
    0.20
     pole
    0.19
    Activations Density 0.021%

    No Known Activations