© 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. 123308
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and developments

    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
    ViewChild
    -0.07
    ãĤ·ãĥ¼
    -0.07
    ลาà¸Ķ
    -0.06
    (/^\
    -0.06
     skal
    -0.06
    dere
    -0.06
    pll
    -0.06
    afs
    -0.06
    æ¼ı
    -0.06
    arda
    -0.06
    POSITIVE LOGITS
     eventually
    0.07
     Eventually
    0.07
    åĩ
    0.07
    elsen
    0.06
    .Event
    0.06
     eventual
    0.06
    lesi
    0.06
    ãĤ¯ãĥĪ
    0.06
    iltr
    0.06
    192
    0.06
    Activations Density 0.002%

    No Known Activations