© 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. 105396
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and form elements

    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
    305
    -0.07
    precated
    -0.06
    lez
    -0.06
    AW
    -0.06
    raph
    -0.06
     Dud
    -0.06
    605
    -0.06
    lico
    -0.06
     Burg
    -0.06
    593
    -0.06
    POSITIVE LOGITS
    UBE
    0.06
    iani
    0.06
    ÂĢ
    0.06
    Xã
    0.06
    _DRV
    0.06
    ControlEvents
    0.06
    ube
    0.06
    âĢŀD
    0.06
    dni
    0.06
    egrity
    0.06
    Activations Density 0.015%

    No Known Activations