© 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. 123260
    Prev
    Next
    INDEX
    Explanations

    phrases related to teaching and parental involvement in children's education

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    rong
    -0.07
    wo
    -0.07
    ersist
    -0.07
    Ñİ
    -0.07
     ju
    -0.07
    itest
    -0.06
    amba
    -0.06
    Ñĸж
    -0.06
    vt
    -0.06
    adelphia
    -0.06
    POSITIVE LOGITS
     children
    0.09
     kids
    0.08
     pint
    0.08
     sons
    0.07
     young
    0.07
     little
    0.07
    ãģ®åŃIJ
    0.07
    ãĥ¼ãĥĭ
    0.07
    aña
    0.07
    children
    0.06
    Activations Density 0.033%

    No Known Activations