© 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. 62441
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and computational data structures

    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
    agens
    -0.07
    .truth
    -0.07
    zell
    -0.07
    ãģľ
    -0.07
    yan
    -0.07
    sterol
    -0.07
    nul
    -0.07
    cie
    -0.06
     OMX
    -0.06
    .newaxis
    -0.06
    POSITIVE LOGITS
    kers
    0.06
     dit
    0.06
     Supervisor
    0.06
     likewise
    0.06
    enter
    0.06
     ebenfalls
    0.06
    Factory
    0.06
    ibrary
    0.05
    ateg
    0.05
    ailer
    0.05
    Activations Density 0.061%

    No Known Activations