© 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. 77616
    Prev
    Next
    INDEX
    Explanations

    numerical and temporal identifiers, such as dates and times

    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
    atters
    -0.06
    ifer
    -0.06
    iez
    -0.06
    eri
    -0.06
     Script
    -0.06
     conn
    -0.06
    ewis
    -0.06
    log
    -0.06
    lou
    -0.05
     lou
    -0.05
    POSITIVE LOGITS
    OwnerId
    0.07
    ÑĪев
    0.07
    imator
    0.07
    .GPIO
    0.07
    /maps
    0.07
     Σε
    0.07
    æµħ
    0.07
    COPE
    0.07
    AndView
    0.07
    folio
    0.06
    Activations Density 0.013%

    No Known Activations