© 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. 80677
    Prev
    Next
    INDEX
    Explanations

    prominent figures and concepts associated with excellence or mastery across various domains

    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
    Äįást
    -0.08
    ummies
    -0.07
    vise
    -0.07
    umas
    -0.07
     اÙĦØŃÙĬ
    -0.07
    ,},↵
    -0.07
    umo
    -0.07
    stal
    -0.07
    amm
    -0.06
    hani
    -0.06
    POSITIVE LOGITS
     among
    0.10
     amongst
    0.10
     of
    0.10
    among
    0.08
     Among
    0.08
     ÑģÑĢеди
    0.08
    级
    0.08
     của
    0.07
    èĪ¬
    0.07
    inth
    0.07
    Activations Density 0.028%

    No Known Activations