© 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. 9-LLAMASCOPE-RES-131K
    11. 99147
    Prev
    Next
    INDEX
    Explanations

    terms related to advocacy or support for a position or theory

    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
    ibraltar
    -0.07
    Äħd
    -0.06
    peare
    -0.06
    åŃĶ
    -0.06
    bron
    -0.06
    aki
    -0.06
    ongan
    -0.06
     zÅĤ
    -0.06
    aghan
    -0.06
    kker
    -0.06
    POSITIVE LOGITS
    èĶµ
    0.07
    æ¢
    0.07
    ãĥ³ãĤº
    0.06
    noch
    0.06
     Introduction
    0.06
    Introduction
    0.06
    èIJ
    0.06
    ipher
    0.06
    others
    0.06
    agma
    0.06
    Activations Density 0.000%

    No Known Activations