© 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. 18629
    Prev
    Next
    INDEX
    Explanations

    references to age and the characteristics associated with aging

    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
     Vie
    -0.06
    à¹Ģà¸Ń
    -0.06
     ad
    -0.06
    ï¼
    -0.06
    ien
    -0.06
     Bale
    -0.06
    723
    -0.06
    lish
    -0.06
    agit
    -0.06
     Bien
    -0.06
    POSITIVE LOGITS
     oneself
    0.09
     must
    0.08
    羣æĺ¯
    0.07
     means
    0.07
    means
    0.07
     знаÑĩиÑĤ
    0.07
    must
    0.07
     Must
    0.07
    Must
    0.07
    requires
    0.07
    Activations Density 0.027%

    No Known Activations