© 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. 89250
    Prev
    Next
    INDEX
    Explanations

    social and economic inequalities affecting specific demographic groups

    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
    оÑĢо
    -0.07
    onic
    -0.07
    etler
    -0.07
    浪
    -0.07
    tres
    -0.07
    eton
    -0.07
    inen
    -0.07
    ÌĨ
    -0.06
    auss
    -0.06
    itemap
    -0.06
    POSITIVE LOGITS
     middle
    0.07
    -middle
    0.07
     tax
    0.07
    middle
    0.07
     median
    0.06
     Tax
    0.06
    beer
    0.06
     soaking
    0.06
     families
    0.06
     soak
    0.06
    Activations Density 0.069%

    No Known Activations