© 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. 2556
    Prev
    Next
    INDEX
    Explanations

    references to search engine optimization and online trends

    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
    locker
    -0.06
    ungal
    -0.06
    ubo
    -0.06
    äd
    -0.06
     Ital
    -0.06
    ayo
    -0.06
     padd
    -0.06
    adb
    -0.06
    arga
    -0.06
    ROM
    -0.06
    POSITIVE LOGITS
    ìĿ´ì§Ģ
    0.07
    elize
    0.07
    jer
    0.07
    rosso
    0.06
    supply
    0.06
     Por
    0.06
    inar
    0.06
    nore
    0.06
     gust
    0.06
    boo
    0.06
    Activations Density 0.003%

    No Known Activations