© 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. 54242
    Prev
    Next
    INDEX
    Explanations

    references to organizational policies and practices related to workplace effectiveness and ethics

    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
    akis
    -0.09
    ãĤ¨ãĥ«
    -0.07
    inya
    -0.07
    lém
    -0.07
    izo
    -0.06
    corn
    -0.06
    bil
    -0.06
    undler
    -0.06
    imator
    -0.06
    AffineTransform
    -0.06
    POSITIVE LOGITS
     employee
    0.06
    ahat
    0.06
     culture
    0.06
    ultur
    0.06
     Employee
    0.06
    aul
    0.06
     cultures
    0.06
     HR
    0.06
     Xiao
    0.06
     reporting
    0.06
    Activations Density 0.003%

    No Known Activations