© 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. 49215
    Prev
    Next
    INDEX
    Explanations

    coloring books & you

    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
     Graphic
    -0.10
    Graphic
    -0.10
    rai
    -0.10
    rien
    -0.09
     discret
    -0.09
     shallow
    -0.09
     pools
    -0.09
    igar
    -0.09
     sparing
    -0.09
     cigar
    -0.09
    POSITIVE LOGITS
     coloring
    0.13
     Modes
    0.13
    Modes
    0.12
     Coloring
    0.11
     HD
    0.11
    abyrin
    0.11
     modes
    0.11
     drawing
    0.10
    eras
    0.10
    çĽĬ
    0.10
    Activations Density 0.032%

    No Known Activations