© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 866
    Prev
    Next
    INDEX
    Explanations

    eyes and gaze

    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
    erli
    -0.09
    UID
    -0.09
    udur
    -0.09
    GenerationStrategy
    -0.09
    lero
    -0.09
    è¾Ľ
    -0.08
     soaring
    -0.08
     poil
    -0.08
    bero
    -0.08
     blasph
    -0.08
    POSITIVE LOGITS
     eyes
    0.48
     Eyes
    0.35
    eyes
    0.34
     eye
    0.31
    çľ¼çĿĽ
    0.30
     gaze
    0.30
     глаза
    0.29
     mắt
    0.28
    çľ¼
    0.28
     look
    0.26
    Activations Density 0.072%

    No Known Activations