© 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. 15-LLAMASCOPE-RES-131K
    11. 89069
    Prev
    Next
    INDEX
    Explanations

    organizational structures and roles within companies

    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
    -INF
    -0.09
    εÏĦ
    -0.08
    ednou
    -0.07
    imli
    -0.07
    IMA
    -0.07
     ìĥĪê¸Ģ
    -0.07
    occo
    -0.07
     thất
    -0.07
    agas
    -0.07
    institution
    -0.07
    POSITIVE LOGITS
     support
    0.07
     supporting
    0.06
     operations
    0.06
     Consumer
    0.06
     core
    0.06
     finance
    0.06
     communications
    0.06
     consumer
    0.06
     Support
    0.06
    kins
    0.06
    Activations Density 0.015%

    No Known Activations