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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3139
    Prev
    Next
    INDEX
    Explanations

    references to immigration and the associated social dynamics

    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
    abb
    -0.09
    /Foundation
    -0.08
     maduras
    -0.08
     sóc
    -0.07
    DSA
    -0.07
    .Mask
    -0.07
    anity
    -0.07
    .epam
    -0.07
    _native
    -0.07
    oba
    -0.07
    POSITIVE LOGITS
     crossing
    0.11
     migration
    0.10
     immigration
    0.09
     Migration
    0.09
     Crossing
    0.09
     migrants
    0.09
     crossings
    0.09
     passage
    0.08
     migrant
    0.08
     Immigration
    0.08
    Activations Density 0.067%

    No Known Activations