© 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. 59624
    Prev
    Next
    INDEX
    Explanations

    references to societal structures and challenges faced by immigrants

    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
    ancia
    -0.08
    licht
    -0.07
    strup
    -0.07
    contri
    -0.07
     Shr
    -0.07
    acerb
    -0.07
    stu
    -0.07
    elda
    -0.07
    @SuppressWarnings
    -0.06
    quip
    -0.06
    POSITIVE LOGITS
     language
    0.08
     NTN
    0.07
     Integration
    0.06
    elez
    0.06
     Language
    0.06
     assim
    0.06
     integration
    0.06
    Integration
    0.06
     social
    0.06
     bi
    0.06
    Activations Density 0.004%

    No Known Activations