© 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. 99018
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals, particularly within royal contexts

    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
    resi
    -0.08
    ãĥ¼ãĤ¹
    -0.07
    _SYNC
    -0.07
     Dün
    -0.07
    abbit
    -0.07
    OTO
    -0.07
    коÑĤ
    -0.07
     Kür
    -0.07
    ëħ¸ì¶ľ
    -0.07
    ress
    -0.06
    POSITIVE LOGITS
     ki
    0.06
    ojis
    0.06
    IGN
    0.06
     Tig
    0.06
    _IA
    0.06
    TypeInfo
    0.05
     Silva
    0.05
    HasKey
    0.05
    veled
    0.05
     Andrews
    0.05
    Activations Density 0.001%

    No Known Activations