© 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. 74519
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions related to preparation and effort

    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
    hra
    -0.06
     Hoy
    -0.06
    ÏĦιν
    -0.06
     grav
    -0.06
    atism
    -0.06
    ä¿Ŀ
    -0.06
    oons
    -0.06
     iam
    -0.06
    HEY
    -0.06
    /mod
    -0.06
    POSITIVE LOGITS
    ec
    0.07
    apter
    0.07
    724
    0.07
    yle
    0.07
    çIJ
    0.07
    before
    0.06
    qi
    0.06
    mit
    0.06
     ago
    0.06
    ussels
    0.06
    Activations Density 0.009%

    No Known Activations