© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88540
    Prev
    Next
    INDEX
    Explanations

    phrases regarding immigration and asylum processes

    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
     Indigenous
    -0.07
    ÙģÙĩ
    -0.07
    wcs
    -0.07
    oro
    -0.07
    angu
    -0.06
    hammer
    -0.06
    oir
    -0.06
    angi
    -0.06
     sang
    -0.06
    indo
    -0.06
    POSITIVE LOGITS
    agram
    0.07
    iglia
    0.07
    ivos
    0.06
    Ñĥнок
    0.06
    é¬
    0.06
    ër
    0.06
     Stall
    0.06
    -await
    0.06
    âr
    0.06
    401
    0.06
    Activations Density 0.014%

    No Known Activations