© 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. 22844
    Prev
    Next
    INDEX
    Explanations

    redhead hair and freckles

    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
     black
    -0.19
    black
    -0.14
     BLACK
    -0.13
     blacks
    -0.13
     Äijen
    -0.12
    é»ij
    -0.12
    -black
    -0.12
    é»Ĵ
    -0.11
     zwarte
    -0.11
     ÑĩоÑĢ
    -0.11
    POSITIVE LOGITS
     Irish
    0.26
     fre
    0.22
     Ireland
    0.21
     redhead
    0.19
     Red
    0.18
    红
    0.16
     red
    0.16
     ginger
    0.16
    Red
    0.16
     Celt
    0.15
    Activations Density 0.033%

    No Known Activations