© 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. 119454
    Prev
    Next
    INDEX
    Explanations

    references to political votes and actions related to government decisions

    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
     bergen
    -0.08
    eÅŁit
    -0.08
    łģ
    -0.08
    ityEngine
    -0.07
    disposed
    -0.07
     åıĮ线
    -0.07
    åħ¬åľĴ
    -0.07
    JSGlobal
    -0.07
     ì§
    -0.07
    idel
    -0.07
    POSITIVE LOGITS
    0.07
     princip
    0.07
     decision
    0.07
     colleague
    0.06
     centr
    0.06
     Esk
    0.06
     vote
    0.06
     Principles
    0.06
     switch
    0.06
     conscience
    0.06
    Activations Density 0.013%

    No Known Activations