© 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. 63283
    Prev
    Next
    INDEX
    Explanations

    terms related to immigration and its associated processes

    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
    ırak
    -0.07
    comings
    -0.07
     kia
    -0.07
    onym
    -0.07
    åĦ¿
    -0.07
    ÑħÑĥ
    -0.07
    ÃŃcÃŃ
    -0.07
    ÙĨب
    -0.07
    NESS
    -0.07
    обÑĢаз
    -0.07
    POSITIVE LOGITS
    zell
    0.08
    /weather
    0.07
    ion
    0.07
    /local
    0.07
    related
    0.06
    /ref
    0.06
    -related
    0.06
    /MPL
    0.06
     status
    0.06
    RefPtr
    0.06
    Activations Density 0.008%

    No Known Activations