© 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 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. 89249
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethics and business sustainability

    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
    inya
    -0.07
    brig
    -0.07
    uja
    -0.07
    инÑĭ
    -0.07
    anova
    -0.06
     Empresa
    -0.06
    velt
    -0.06
    atron
    -0.06
    raž
    -0.06
    itia
    -0.06
    POSITIVE LOGITS
     Pins
    0.06
     Spend
    0.06
    CEE
    0.06
     survivor
    0.06
    è¾ij
    0.06
    >Returns
    0.06
    ingleton
    0.06
    ê¶Į
    0.06
    tplib
    0.06
    702
    0.06
    Activations Density 0.003%

    No Known Activations