© 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. 124890
    Prev
    Next
    INDEX
    Explanations

    references to social identity and class status

    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
    ænd
    -0.07
    unas
    -0.07
    raç
    -0.07
    uards
    -0.07
    ighb
    -0.07
    ivery
    -0.06
    adesh
    -0.06
    kün
    -0.06
     capit
    -0.06
     phái
    -0.06
    POSITIVE LOGITS
     humble
    0.13
     modest
    0.10
     ordinary
    0.10
     prolet
    0.10
     humility
    0.10
     grass
    0.09
     normal
    0.08
     lower
    0.08
     simple
    0.08
     regular
    0.08
    Activations Density 0.026%

    No Known Activations