© 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. 30570
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration and eligibility criteria

    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
    allax
    -0.07
     ฿
    -0.06
    aye
    -0.06
     Gaul
    -0.06
    unta
    -0.06
    ượng
    -0.06
    argin
    -0.06
    asti
    -0.06
    /goto
    -0.06
    cott
    -0.06
    POSITIVE LOGITS
     immigration
    0.10
     migration
    0.09
     Migration
    0.09
    Migration
    0.08
     immigr
    0.07
     Immigration
    0.07
     em
    0.07
     immigrants
    0.07
     migrate
    0.07
    migration
    0.06
    Activations Density 0.001%

    No Known Activations