© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14066
    Prev
    Next
    INDEX
    Explanations

    blue player, with businesses, displays map

    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
     shaded
    -0.14
     desn
    -0.11
     insets
    -0.10
     inset
    -0.10
     Inches
    -0.09
     Dimensions
    -0.09
     planes
    -0.09
     dimensions
    -0.09
     éĤ
    -0.09
    å±ı
    -0.09
    POSITIVE LOGITS
     solid
    0.17
     green
    0.17
     legend
    0.16
     filled
    0.16
     lines
    0.16
     circ
    0.16
     black
    0.14
     bars
    0.14
     hatch
    0.14
     Solid
    0.13
    Activations Density 0.082%

    No Known Activations