© 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. 29939
    Prev
    Next
    INDEX
    Explanations

    historical narratives and legends

    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
    adj
    -0.07
    amera
    -0.07
    holm
    -0.07
    .appspot
    -0.06
     onto
    -0.06
     intl
    -0.06
    arin
    -0.06
     wParam
    -0.06
    μη
    -0.06
    abus
    -0.06
    POSITIVE LOGITS
    yne
    0.07
    ROWSER
    0.07
     Sims
    0.06
    _SF
    0.06
    thal
    0.06
    edis
    0.06
    anvas
    0.06
    anship
    0.06
     modem
    0.06
     bahis
    0.06
    Activations Density 0.007%

    No Known Activations