© 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. 58135
    Prev
    Next
    INDEX
    Explanations

    phrases related to evidence-based practices in public health 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
    kus
    -0.07
     dual
    -0.06
    Dual
    -0.06
    mouseup
    -0.06
    ebra
    -0.06
     Ft
    -0.06
     Cork
    -0.06
    eral
    -0.06
     Dual
    -0.05
    911
    -0.05
    POSITIVE LOGITS
     evidence
    0.10
     Evidence
    0.09
    Evidence
    0.09
     effectiveness
    0.09
    Meta
    0.08
    TRL
    0.08
    meta
    0.08
     Meta
    0.08
    RCT
    0.07
    inions
    0.07
    Activations Density 0.038%

    No Known Activations