© 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. 12994
    Prev
    Next
    INDEX
    Explanations

    the flowers

    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
     botanical
    -0.14
     leaf
    -0.12
     Leaf
    -0.10
    idon
    -0.10
     Zucker
    -0.09
     plac
    -0.09
    _leaf
    -0.09
    Leaf
    -0.09
     سبز
    -0.09
    neau
    -0.09
    POSITIVE LOGITS
     flowers
    0.25
    èĬ±
    0.24
    flowers
    0.23
     rose
    0.22
     roses
    0.22
     Rose
    0.22
     ÑĨвеÑĤ
    0.21
     tul
    0.21
     carn
    0.19
    ê½
    0.19
    Activations Density 0.151%

    No Known Activations