© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74497
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers describing entities or groups

    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
    empre
    -0.08
    inerary
    -0.08
     yans
    -0.07
    rene
    -0.07
     Lage
    -0.07
    .gb
    -0.07
    IALIZED
    -0.07
    Interop
    -0.07
    ï¿
    -0.07
    -uri
    -0.07
    POSITIVE LOGITS
    ernen
    0.06
    plementation
    0.06
    activex
    0.06
    ead
    0.06
    ureau
    0.06
    ÑĢÑı
    0.06
    ziej
    0.06
    rollo
    0.06
    mlink
    0.06
    üss
    0.06
    Activations Density 0.226%

    No Known Activations