© 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. 118869
    Prev
    Next
    INDEX
    Explanations

    references to politicians and political figures

    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
    leigh
    -0.09
    nees
    -0.08
    ScrollIndicator
    -0.08
    /Typography
    -0.07
    celik
    -0.07
    主任
    -0.07
    anja
    -0.07
    loh
    -0.07
    ingt
    -0.07
    ibil
    -0.07
    POSITIVE LOGITS
    ural
    0.08
     who
    0.07
    à¥Ģय
    0.07
    ilestone
    0.07
    heck
    0.06
     CDs
    0.06
    们
    0.06
    unction
    0.06
    opause
    0.06
    ically
    0.06
    Activations Density 0.014%

    No Known Activations