© 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. 40387
    Prev
    Next
    INDEX
    Explanations

    references to citizen science and its applications

    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
    ardown
    -0.08
    ungan
    -0.07
    uncture
    -0.07
    emark
    -0.07
    hire
    -0.06
    opies
    -0.06
     Demir
    -0.06
    ernes
    -0.06
    Fixture
    -0.06
     Classe
    -0.06
    POSITIVE LOGITS
     tasks
    0.07
     Virtual
    0.07
     online
    0.07
     Instructions
    0.06
     virtual
    0.06
     instructions
    0.06
    tasks
    0.06
     Auxiliary
    0.06
     missions
    0.06
    ear
    0.06
    Activations Density 0.001%

    No Known Activations