© 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. 46457
    Prev
    Next
    INDEX
    Explanations

    describing physical attributes

    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
     slender
    -0.16
     Skinny
    -0.14
     chubby
    -0.14
     skinny
    -0.14
    Slim
    -0.13
     Slim
    -0.13
     slim
    -0.13
     obese
    -0.12
    身ä½ĵ
    -0.11
     overweight
    -0.11
    POSITIVE LOGITS
     strength
    0.11
     mus
    0.11
     hands
    0.10
     face
    0.10
     Voice
    0.10
     faces
    0.10
     facial
    0.10
     height
    0.09
     Faces
    0.09
     Ravens
    0.09
    Activations Density 0.072%

    No Known Activations