© 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. 9-LLAMASCOPE-RES-131K
    11. 98107
    Prev
    Next
    INDEX
    Explanations

    references to fairy tales, particularly those by the Grimm brothers

    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
    uilder
    -0.07
    hind
    -0.07
    adio
    -0.07
     ë§ŀ
    -0.07
     serialVersionUID
    -0.06
    nder
    -0.06
    jekt
    -0.06
    ItemSelectedListener
    -0.06
     Praze
    -0.06
    åĪļæīį
    -0.06
    POSITIVE LOGITS
    nes
    0.06
    SPA
    0.06
    (AT
    0.06
     reve
    0.06
    _SPI
    0.06
     SPA
    0.06
     Country
    0.06
     country
    0.06
     collection
    0.06
     __("
    0.06
    Activations Density 0.003%

    No Known Activations