© 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. 84532
    Prev
    Next
    INDEX
    Explanations

    references to the Affordable Care Act (Obamacare) and its implications

    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
    .scalablytyped
    -0.06
    itarian
    -0.06
    رÙĪز
    -0.06
     Kraj
    -0.06
    olt
    -0.06
    ä¹ĭä¸Ģ
    -0.06
    ikt
    -0.06
    (Editor
    -0.06
    ecz
    -0.06
     addAction
    -0.06
    POSITIVE LOGITS
    ipay
    0.07
    upe
    0.07
    -era
    0.06
     hiá»ĥm
    0.06
    ucher
    0.06
    _COMPAT
    0.06
     Cyril
    0.06
    unas
    0.06
    upp
    0.06
     fitte
    0.06
    Activations Density 0.003%

    No Known Activations