© 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. 15716
    Prev
    Next
    INDEX
    Explanations

    elements related to administrative processes and grant management

    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
    isko
    -0.07
     concessions
    -0.07
    Ỽ
    -0.06
    ÑĪка
    -0.06
    SDL
    -0.06
    SystemService
    -0.06
     GOODMAN
    -0.06
    ади
    -0.06
    isses
    -0.06
    atern
    -0.06
    POSITIVE LOGITS
     project
    0.10
    über
    0.08
     reporting
    0.07
    -project
    0.07
    /project
    0.07
     Project
    0.07
    beit
    0.07
    Project
    0.07
     accounting
    0.07
    uria
    0.07
    Activations Density 0.006%

    No Known Activations