© 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. 42676
    Prev
    Next
    INDEX
    Explanations

    themes related to accountability and consequences of actions

    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
     Vám
    -0.07
     خرد
    -0.06
    ãģ¾
    -0.06
    окÑĢем
    -0.06
    283
    -0.06
    395
    -0.06
     Wo
    -0.06
    asso
    -0.06
    ãĤ´ãĥª
    -0.06
    rh
    -0.06
    POSITIVE LOGITS
    ongyang
    0.07
    ÅĻe
    0.07
    ROTO
    0.07
    ampus
    0.06
    ute
    0.06
    ãĥ¼ãĤ¹ãĥĪ
    0.06
    tingham
    0.06
     ÙħÙħÙĨ
    0.06
     lanc
    0.06
    _exempt
    0.06
    Activations Density 0.081%

    No Known Activations