© 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. 17-LLAMASCOPE-RES-131K
    11. 125424
    Prev
    Next
    INDEX
    Explanations

    key terms related to economic and political transitions

    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
    etus
    -0.08
    aname
    -0.08
    /fw
    -0.08
    лÑĥÑĩ
    -0.08
    год
    -0.07
    ibus
    -0.07
    èĹ
    -0.07
    rán
    -0.07
    аÑĤок
    -0.07
    ingleton
    -0.07
    POSITIVE LOGITS
     Athens
    0.10
     Greek
    0.10
     Greece
    0.09
     Greeks
    0.07
     EU
    0.07
     Corinth
    0.07
     Gree
    0.06
    Greek
    0.06
     Gre
    0.06
     Orthodox
    0.06
    Activations Density 0.000%

    No Known Activations