© 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. 80673
    Prev
    Next
    INDEX
    Explanations

    references to the Council of Europe and its activities related to human rights and child protection

    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
     Turnbull
    -0.07
     Modeling
    -0.07
     statewide
    -0.07
    umpt
    -0.06
    ASTER
    -0.06
    adiens
    -0.06
     modeling
    -0.06
    posables
    -0.06
     Zá
    -0.06
    eres
    -0.06
    POSITIVE LOGITS
    丶
    0.07
    bero
    0.07
     Aub
    0.07
     Forum
    0.07
    oeff
    0.06
     Bieber
    0.06
     Erg
    0.06
     Atlantic
    0.06
     Gros
    0.06
     subsidi
    0.06
    Activations Density 0.011%

    No Known Activations