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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27121
    Prev
    Next
    INDEX
    Explanations

    terms related to immigration status and eligibility criteria for residency

    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
    antz
    -0.07
    icher
    -0.07
    OptionsResolver
    -0.07
    allis
    -0.07
    zcze
    -0.07
    etros
    -0.07
    ogan
    -0.06
    okino
    -0.06
    dex
    -0.06
    velle
    -0.06
    POSITIVE LOGITS
     statuses
    0.08
     ÙħÙĪاط
    0.07
     status
    0.07
    -status
    0.06
     foreign
    0.06
    iny
    0.06
     admir
    0.06
    status
    0.06
     æı
    0.06
    foreign
    0.06
    Activations Density 0.008%

    No Known Activations