© 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. 16542
    Prev
    Next
    INDEX
    Explanations

    references to different types of healthcare interventions and control groups in studies

    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
    ilm
    -0.07
    лади
    -0.06
    LONG
    -0.06
    portal
    -0.06
    ron
    -0.06
    tron
    -0.06
    lsen
    -0.06
    iones
    -0.06
    ules
    -0.06
    /module
    -0.06
    POSITIVE LOGITS
     standard
    0.10
    usual
    0.08
     practices
    0.08
     typical
    0.08
     usual
    0.08
    baseline
    0.08
    standard
    0.08
     baseline
    0.08
     practice
    0.07
    -standard
    0.07
    Activations Density 0.029%

    No Known Activations