© 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. 9-LLAMASCOPE-RES-131K
    11. 95766
    Prev
    Next
    INDEX
    Explanations

    terms related to power management and device states

    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
     umb
    -0.07
    ERA
    -0.06
    iddi
    -0.06
    undos
    -0.06
    uslim
    -0.06
     Umb
    -0.06
    ective
    -0.06
    stag
    -0.06
     lao
    -0.06
     Ezra
    -0.06
    POSITIVE LOGITS
    avl
    0.07
    olec
    0.07
    cie
    0.07
    bras
    0.06
    Atlantic
    0.06
    wards
    0.06
    otti
    0.06
    $http
    0.06
    esion
    0.06
    razier
    0.06
    Activations Density 0.021%

    No Known Activations