© 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. 38827
    Prev
    Next
    INDEX
    Explanations

    references to various forms of societal roles and activities, particularly in community service and labor contexts

    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
    adele
    -0.07
    olor
    -0.07
    illac
    -0.07
    LEMENT
    -0.07
    eed
    -0.07
     ******************************************************************************↵
    -0.06
    боÑĢ
    -0.06
    obar
    -0.06
    ael
    -0.06
     Aub
    -0.06
    POSITIVE LOGITS
    redients
    0.07
    ër
    0.07
    phy
    0.07
    ers
    0.07
     iParam
    0.06
    ERS
    0.06
    cape
    0.06
     excellence
    0.06
    und
    0.06
    itch
    0.06
    Activations Density 0.066%

    No Known Activations