© 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. 89451
    Prev
    Next
    INDEX
    Explanations

    references to iconic advertisements and signage

    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
    USART
    -0.06
     etiqu
    -0.06
    imbus
    -0.06
    GenerationStrategy
    -0.06
    gression
    -0.06
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.06
    ucha
    -0.06
     delegation
    -0.06
     вк
    -0.06
     tu
    -0.06
    POSITIVE LOGITS
     neon
    0.07
     billboard
    0.07
    çīĮ
    0.06
    /logo
    0.06
     outdoor
    0.06
     display
    0.06
    Street
    0.06
     Neon
    0.06
    <message
    0.06
     window
    0.06
    Activations Density 0.009%

    No Known Activations