© 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. 18772
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to physical processes and materials

    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
    odon
    -0.07
    otti
    -0.07
    ÃĹ</
    -0.06
    dorf
    -0.06
    quette
    -0.06
    姿
    -0.06
    uem
    -0.06
    екÑģи
    -0.06
     DOWN
    -0.06
    orz
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    arg
    0.07
    0.06
    proved
    0.06
     microscopic
    0.06
    浩
    0.06
    &id
    0.06
    ptal
    0.06
    ITT
    0.06
    нод
    0.06
    Activations Density 0.021%

    No Known Activations