© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80144
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration and the experiences of immigrant groups

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    peria
    -0.07
    zburg
    -0.06
    agn
    -0.06
    oba
    -0.06
    Asia
    -0.06
    uji
    -0.06
    ritz
    -0.06
    ê¸ī
    -0.06
    кеÑĤ
    -0.06
    oir
    -0.06
    POSITIVE LOGITS
     USA
    0.20
     American
    0.19
     America
    0.19
     СШÐIJ
    0.19
     US
    0.18
    USA
    0.18
    ç¾İåĽ½
    0.18
     Americans
    0.17
    American
    0.17
    ç¾İåľĭ
    0.17
    Activations Density 0.238%

    No Known Activations