© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 99051
    Prev
    Next
    INDEX
    Explanations

    terms related to different types of brushes used in various contexts, particularly in art and painting

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    cheng
    -0.08
    Ñħо
    -0.07
    chai
    -0.07
    rrha
    -0.07
    estic
    -0.07
    ën
    -0.07
    Href
    -0.07
    gers
    -0.07
    nbsp
    -0.07
    hue
    -0.07
    POSITIVE LOGITS
    (es
    0.09
    icket
    0.06
    åĽ£
    0.06
    immer
    0.06
    ES
    0.06
    기ìĪł
    0.06
    Ñĥмов
    0.06
    266
    0.05
    430
    0.05
    rut
    0.05
    Activations Density 0.006%

    No Known Activations