© 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. 108544
    Prev
    Next
    INDEX
    Explanations

    phrases indicating mathematical relationships and properties

    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
    frage
    -0.06
     hormones
    -0.06
     Richt
    -0.06
    fdc
    -0.06
    agina
    -0.06
    ãģĤãģĴ
    -0.06
    ym
    -0.06
    ERV
    -0.06
    ³
    -0.06
    .vn
    -0.06
    POSITIVE LOGITS
    ÎŃνÏĦ
    0.07
    quist
    0.07
     structure
    0.07
    ìĿ´ìĬ¤
    0.07
    à¥įमà¤ķ
    0.07
    δι
    0.07
    edBy
    0.06
    strup
    0.06
    andro
    0.06
    structure
    0.06
    Activations Density 0.056%

    No Known Activations