© 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. 99176
    Prev
    Next
    INDEX
    Explanations

    phrases related to accessibility and advocacy in voting and employment 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
     Ot
    -0.06
    holm
    -0.06
    Ñģм
    -0.06
     TMPro
    -0.06
    rens
    -0.06
    İĺìĿ´
    -0.06
    vip
    -0.06
    οÏģ
    -0.06
    otp
    -0.05
    alis
    -0.05
    POSITIVE LOGITS
    ichert
    0.09
    Ïģοι
    0.06
    æ²¢
    0.06
    ToAdd
    0.06
    iah
    0.06
    ÑĢÑĭ
    0.06
     ÙħÙĪتÙĪر
    0.06
    simd
    0.06
    .RELATED
    0.06
     Maui
    0.06
    Activations Density 0.012%

    No Known Activations