© 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 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. 84317
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to resources and opportunities available for learning and education

    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
     ill
    -0.07
     ot
    -0.06
     circulation
    -0.06
     will
    -0.06
    pek
    -0.06
    hap
    -0.06
     please
    -0.06
     used
    -0.05
     set
    -0.05
     mist
    -0.05
    POSITIVE LOGITS
     Wayback
    0.08
    afa
    0.08
    Broken
    0.08
     Broken
    0.07
    ìĽ¨
    0.07
    zÄĻ
    0.07
    uego
    0.07
    лади
    0.07
    loff
    0.07
    991
    0.07
    Activations Density 0.004%

    No Known Activations