© 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. 61484
    Prev
    Next
    INDEX
    Explanations

    references to gender roles and the contributions of women in caregiving and household tasks

    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
    raç
    -0.07
    itage
    -0.07
    igin
    -0.06
    deen
    -0.06
    lox
    -0.06
    ODO
    -0.06
    ampo
    -0.06
    imuth
    -0.06
     Sheep
    -0.06
    igos
    -0.06
    POSITIVE LOGITS
     unpaid
    0.10
     household
    0.10
     labour
    0.09
     Household
    0.08
     labor
    0.08
     tasks
    0.08
     women
    0.08
     chores
    0.08
     caring
    0.07
     invis
    0.07
    Activations Density 0.006%

    No Known Activations