© 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. 81974
    Prev
    Next
    INDEX
    Explanations

    references to visa and legal residency issues related to 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
    ason
    -0.07
    aben
    -0.06
     DISCLAIM
    -0.06
    Cert
    -0.06
     derec
    -0.06
    áme
    -0.06
    ene
    -0.06
     Cer
    -0.06
    urst
    -0.06
    Alive
    -0.06
    POSITIVE LOGITS
     visa
    0.12
     immigration
    0.12
     immigr
    0.10
     visas
    0.10
     Immigration
    0.09
    visa
    0.08
     permit
    0.08
     immigrant
    0.08
    Imm
    0.08
     Visa
    0.08
    Activations Density 0.033%

    No Known Activations