© 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. 17-LLAMASCOPE-RES-131K
    11. 61696
    Prev
    Next
    INDEX
    Explanations

    references to the elements and structure of performance art and literature

    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
     nab
    -0.07
    udas
    -0.07
    ergy
    -0.07
    -0.06
    AppState
    -0.06
    innen
    -0.06
     ev
    -0.06
    _contr
    -0.06
    รà¸ĵ
    -0.06
    ùa
    -0.06
    POSITIVE LOGITS
    лÑĥÑĩ
    0.07
     Recent
    0.06
    tr
    0.06
    eurs
    0.06
    arga
    0.06
    øy
    0.06
     Horm
    0.06
    oi
    0.06
    othy
    0.06
    ocene
    0.06
    Activations Density 0.003%

    No Known Activations