© 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. 92655
    Prev
    Next
    INDEX
    Explanations

    quantitative data and organizational structures

    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
     hete
    -0.08
    htub
    -0.08
    /***/
    -0.08
    amax
    -0.07
    uben
    -0.07
    ův
    -0.07
    .addRow
    -0.07
    ÑĪка
    -0.07
    wij
    -0.07
    gow
    -0.07
    POSITIVE LOGITS
     worldwide
    0.09
     across
    0.08
     globally
    0.08
     branches
    0.08
     sites
    0.08
     locations
    0.07
     branch
    0.07
     campuses
    0.07
     global
    0.07
     employees
    0.07
    Activations Density 0.016%

    No Known Activations