© 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. 30091
    Prev
    Next
    INDEX
    Explanations

    external appearance surface

    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
     exagger
    -0.11
     imperson
    -0.09
     Sne
    -0.09
     exaggerated
    -0.09
    ebo
    -0.09
    éĵº
    -0.09
    952
    -0.09
    'gc
    -0.09
     exclusion
    -0.09
    -spacing
    -0.08
    POSITIVE LOGITS
     appearances
    0.36
     exterior
    0.34
     surface
    0.34
     appearance
    0.32
     outer
    0.27
     Surface
    0.27
    å¤ĸ
    0.27
     extern
    0.26
     Exterior
    0.26
    surface
    0.25
    Activations Density 0.149%

    No Known Activations