© 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. 99268
    Prev
    Next
    INDEX
    Explanations

    terms related to bestselling books and authors

    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
    aket
    -0.07
    ubern
    -0.06
    inite
    -0.06
    μοί
    -0.06
    apy
    -0.06
    éné
    -0.06
    lide
    -0.06
    andy
    -0.06
    angi
    -0.06
    uth
    -0.06
    POSITIVE LOGITS
    eÄį
    0.07
    /pop
    0.07
     Johnston
    0.07
    QUENCY
    0.06
    816
    0.06
    ÄĻk
    0.06
    dust
    0.06
    aug
    0.06
    holm
    0.06
    escort
    0.06
    Activations Density 0.004%

    No Known Activations