© 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. 84320
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks and actions that need to be completed

    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
     HeaderComponent
    -0.07
    apikey
    -0.07
    ishment
    -0.06
    mente
    -0.06
     Breed
    -0.06
    morgan
    -0.06
    adele
    -0.06
    istické
    -0.06
    inski
    -0.06
    ág
    -0.06
    POSITIVE LOGITS
    ater
    0.08
    rys
    0.07
     worry
    0.07
     contend
    0.07
    uro
    0.06
    swire
    0.06
    subtotal
    0.06
    ile
    0.06
    anto
    0.06
    _completion
    0.06
    Activations Density 0.013%

    No Known Activations