© 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. 128742
    Prev
    Next
    INDEX
    Explanations

    references to political and social crises within the context of immigration and public policy

    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
    elez
    -0.07
    dül
    -0.07
    ieber
    -0.07
    êt
    -0.07
    ignon
    -0.06
    chen
    -0.06
    emd
    -0.06
    ench
    -0.06
     Υ
    -0.06
    emmel
    -0.06
    POSITIVE LOGITS
     Maj
    0.06
    ableObject
    0.06
     "[
    0.06
    Advertisement
    0.06
    ModelIndex
    0.06
    ->__
    0.06
     proble
    0.06
     Incredible
    0.06
     serg
    0.06
    _meter
    0.06
    Activations Density 0.007%

    No Known Activations