© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89543
    Prev
    Next
    INDEX
    Explanations

    terms related to momentum and transfer in a scientific or mathematical context

    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
    oya
    -0.07
    onta
    -0.06
    618
    -0.06
    keit
    -0.06
    869
    -0.06
    pery
    -0.06
    737
    -0.06
    arus
    -0.06
    mente
    -0.06
    731
    -0.06
    POSITIVE LOGITS
     eskort
    0.07
    Та
    0.07
    ↵↵
    0.07
    иÑģÑĤÑĢа
    0.07
    QS
    0.07
    é½
    0.07
    CHIP
    0.07
     reklam
    0.07
    заб
    0.07
     rodi
    0.07
    Activations Density 0.038%

    No Known Activations