© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4578
    Prev
    Next
    INDEX
    Explanations

    programming and HTML elements related to web development functionality

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    aub
    -0.08
    ëĦ·
    -0.07
    alis
    -0.07
    bish
    -0.07
    reff
    -0.07
    agate
    -0.07
     webcam
    -0.07
    aed
    -0.07
    askell
    -0.07
    /Dk
    -0.07
    POSITIVE LOGITS
    Nonce
    0.08
     Gutenberg
    0.08
     wp
    0.08
     WordPress
    0.08
    wpdb
    0.08
     WP
    0.07
    (wp
    0.07
    WordPress
    0.07
    wp
    0.07
     Beaver
    0.07
    Activations Density 0.145%

    No Known Activations