© 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. 95279
    Prev
    Next
    INDEX
    Explanations

    references to historical places and events

    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
    æ´²
    -0.07
     Aquarium
    -0.07
     provinces
    -0.07
     дейÑģÑĤвиÑı
    -0.07
    岸
    -0.07
     Arthropoda
    -0.07
    (states
    -0.07
    states
    -0.07
     states
    -0.07
    å»Ĭ
    -0.07
    POSITIVE LOGITS
     history
    0.09
    history
    0.08
    elere
    0.08
     History
    0.08
    _history
    0.07
     histories
    0.07
    History
    0.07
    .history
    0.07
     иÑģÑĤоÑĢ
    0.07
     HISTORY
    0.07
    Activations Density 0.033%

    No Known Activations