© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31408
    Prev
    Next
    INDEX
    Explanations

    concepts related to familial obligations and societal expectations

    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
    aint
    -0.08
    oui
    -0.08
    agos
    -0.07
    878
    -0.07
    metis
    -0.07
    ÑĬем
    -0.07
     Prev
    -0.07
     quiz
    -0.06
    igo
    -0.06
    outil
    -0.06
    POSITIVE LOGITS
     Cuisine
    0.06
    AMESPACE
    0.06
     [
    0.06
     McCart
    0.06
    MOOTH
    0.06
     Griffith
    0.06
    anda
    0.06
     kad
    0.05
    [at
    0.05
    anja
    0.05
    Activations Density 0.001%

    No Known Activations