© 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. 89708
    Prev
    Next
    INDEX
    Explanations

    technical terms related to user interface controls and event handling in programming

    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
    hum
    -0.08
    زÙħ
    -0.06
    uron
    -0.06
    DataGridViewTextBoxColumn
    -0.06
    SD
    -0.06
    lut
    -0.06
    ovice
    -0.06
    nowledge
    -0.05
    γÏģά
    -0.05
    uki
    -0.05
    POSITIVE LOGITS
     mimeType
    0.07
    ynch
    0.07
     ATI
    0.07
    tempts
    0.06
     GIF
    0.06
    eria
    0.06
     âĹĦ
    0.06
    ाà¤ģ
    0.06
    sob
    0.06
     Casc
    0.06
    Activations Density 0.006%

    No Known Activations