© 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 EvalsExportsinterp-engineNEWAPI 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. 95450
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to agreements and legal or regulatory frameworks

    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
    aeda
    -0.09
    ãĥ»ãĥ»ãĥ»
    -0.09
    ÅĻÃŃzenÃŃ
    -0.09
    ÅĻád
    -0.09
    lemn
    -0.09
    ноз
    -0.09
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.09
    rouw
    -0.08
    Ậ
    -0.08
     ıs
    -0.08
    POSITIVE LOGITS
     etc
    0.06
     bustling
    0.06
     sidelines
    0.06
    ificados
    0.05
    alez
    0.05
     respective
    0.05
     quaint
    0.05
    оÑĢаÑı
    0.05
     parenthesis
    0.05
     sins
    0.05
    Activations Density 0.003%

    No Known Activations