© 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. 92885
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes related to icons and navigation elements in a user interface

    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
    azzi
    -0.07
    atus
    -0.06
    wap
    -0.06
    ipi
    -0.06
    adora
    -0.06
    ῶ
    -0.06
    Æ°á»Łng
    -0.06
    ãģ£ãģ±ãģĦ
    -0.06
    ooter
    -0.06
    claimer
    -0.06
    POSITIVE LOGITS
     href
    0.09
    [href
    0.08
     Anchor
    0.07
    href
    0.07
     link
    0.07
    link
    0.07
    Anchor
    0.07
    (href
    0.07
     anchor
    0.07
    _link
    0.07
    Activations Density 0.010%

    No Known Activations