© 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. 121480
    Prev
    Next
    INDEX
    Explanations

    references to government administrations and their policies

    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
     æĻ´
    -0.07
    ãĤ¤ãĤº
    -0.07
    -layout
    -0.07
    omite
    -0.07
    emek
    -0.07
    ritz
    -0.07
    subcategory
    -0.07
    jong
    -0.07
     UIL
    -0.07
    .ba
    -0.07
    POSITIVE LOGITS
     likely
    0.08
     incoming
    0.07
    ãģŃ
    0.06
     change
    0.06
     Change
    0.06
    likely
    0.06
    iu
    0.06
    ylum
    0.06
     sleeper
    0.06
    angi
    0.06
    Activations Density 0.020%

    No Known Activations