© 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. 63275
    Prev
    Next
    INDEX
    Explanations

    references to ages or age-related information in obituaries

    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
    же
    -0.07
    /lists
    -0.07
     Gover
    -0.07
     Gratuit
    -0.07
    hab
    -0.07
    Ú¯ÙĪÙĨÙĩ
    -0.07
    als
    -0.06
    Forbidden
    -0.06
    ви
    -0.06
    ender
    -0.06
    POSITIVE LOGITS
    ĥn
    0.07
    ère
    0.06
    asha
    0.06
    uchen
    0.06
     pres
    0.06
    onia
    0.06
    scriptId
    0.06
     ob
    0.06
    inality
    0.06
     grav
    0.06
    Activations Density 0.004%

    No Known Activations