© 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. 99148
    Prev
    Next
    INDEX
    Explanations

    expressions of personal thoughts and hesitations

    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
    lak
    -0.07
    vens
    -0.07
    bing
    -0.07
    ilip
    -0.06
    .openg
    -0.06
    mada
    -0.06
    quette
    -0.06
    GenerationStrategy
    -0.06
    swick
    -0.06
    ints
    -0.06
    POSITIVE LOGITS
     Idol
    0.07
    اسÙĩ
    0.07
    igm
    0.06
     therap
    0.06
    ="<<
    0.06
    missive
    0.06
    Ø´ÛĮ
    0.06
     Bever
    0.06
    ENCIL
    0.06
    /reset
    0.06
    Activations Density 0.029%

    No Known Activations