© 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. 92012
    Prev
    Next
    INDEX
    Explanations

    expressions of creativity and collaboration among individuals

    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
    kova
    -0.07
    venes
    -0.07
    alue
    -0.07
     GANG
    -0.07
    prak
    -0.06
    esty
    -0.06
    åIJ¹
    -0.06
    084
    -0.06
     Barth
    -0.06
    bé
    -0.06
    POSITIVE LOGITS
    chosen
    0.06
    SystemService
    0.06
    kee
    0.06
     physiology
    0.06
    commerce
    0.06
    Commerce
    0.06
     Rub
    0.06
    -scrollbar
    0.06
    SenderId
    0.06
     prest
    0.06
    Activations Density 0.052%

    No Known Activations