© 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. 129530
    Prev
    Next
    INDEX
    Explanations

    verbs related to the start or initiation of actions

    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
     ÏĥÏħνÎŃ
    -0.07
     Bản
    -0.07
    kills
    -0.07
    она
    -0.07
    abama
    -0.07
     Rencontre
    -0.07
    าà¸ĩ
    -0.07
     Johnston
    -0.07
    llib
    -0.07
    ought
    -0.07
    POSITIVE LOGITS
    nings
    0.14
    /end
    0.08
     to
    0.07
    953
    0.07
     anew
    0.07
    ImageContext
    0.07
    OfDay
    0.06
    iant
    0.06
     innings
    0.06
    OfWeek
    0.06
    Activations Density 0.024%

    No Known Activations