© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14657
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a source of energy or power

    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
     Laurel
    -0.07
    ods
    -0.07
    \CMS
    -0.07
    ebek
    -0.07
    .qq
    -0.07
    inz
    -0.06
    iá»ĩn
    -0.06
    itus
    -0.06
    باز
    -0.06
    nesia
    -0.06
    POSITIVE LOGITS
     powered
    0.07
    247
    0.07
    enticate
    0.06
    lingen
    0.06
    powers
    0.06
    swers
    0.06
    ock
    0.06
    emales
    0.06
     Pink
    0.06
    -powered
    0.06
    Activations Density 0.003%

    No Known Activations