© 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. 17-LLAMASCOPE-RES-131K
    11. 27077
    Prev
    Next
    INDEX
    Explanations

    numerical values and sizes related to web design or CSS properties

    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
    aukee
    -0.08
    rsa
    -0.07
     ($)
    -0.07
    fallback
    -0.07
    práv
    -0.07
    ecta
    -0.07
    onec
    -0.07
    ilee
    -0.07
    окÑĢем
    -0.06
    ilis
    -0.06
    POSITIVE LOGITS
    px
    0.08
    pt
    0.06
    ius
    0.06
    /setup
    0.06
    ICA
    0.06
     Ark
    0.06
    him
    0.06
    ATA
    0.06
    innitus
    0.06
     Keller
    0.06
    Activations Density 0.017%

    No Known Activations