© 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. 5-LLAMASCOPE-RES-131K
    11. 126025
    Prev
    Next
    INDEX
    Explanations

    references to specific countries and their contexts

    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
     over
    -0.06
     pre
    -0.06
     than
    -0.05
    er
    -0.05
     Shell
    -0.05
    âĢ¦↵
    -0.05
     Pop
    -0.05
     Anton
    -0.05
     contrast
    -0.05
     Rot
    -0.05
    POSITIVE LOGITS
    ancel
    0.08
    ynet
    0.08
    arris
    0.07
    .dk
    0.07
    .unbind
    0.07
    ynchronized
    0.07
    presso
    0.07
    ίοÏĤ
    0.07
    anning
    0.07
    ugas
    0.07
    Activations Density 0.038%

    No Known Activations