© 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. 116504
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and funding related to government relief efforts

    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
    EMPL
    -0.08
    ëªħ
    -0.07
    eware
    -0.06
    ocl
    -0.06
    auf
    -0.06
    vyk
    -0.06
     Tal
    -0.06
     Cup
    -0.06
    unca
    -0.06
    UF
    -0.06
    POSITIVE LOGITS
     provisions
    0.08
    ago
    0.07
    zych
    0.06
     Omn
    0.06
    ogi
    0.06
     formula
    0.06
    scri
    0.06
    ога
    0.06
    åł
    0.06
    ju
    0.06
    Activations Density 0.009%

    No Known Activations