© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126687
    Prev
    Next
    INDEX
    Explanations

    references to legislative bodies or political systems

    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
    usi
    -0.07
    Mono
    -0.06
    pus
    -0.06
    rams
    -0.06
    pri
    -0.06
    erse
    -0.06
    ampion
    -0.06
    riends
    -0.06
    nou
    -0.06
    uela
    -0.06
    POSITIVE LOGITS
    edriver
    0.07
    æĭĵ
    0.07
    rowser
    0.06
    ".$_
    0.06
     Hampton
    0.06
    kich
    0.06
    oblin
    0.06
    atoria
    0.06
    raci
    0.06
    issing
    0.06
    Activations Density 0.000%

    No Known Activations