© 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. 17-LLAMASCOPE-RES-131K
    11. 55622
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues and governmental structures

    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
    алÑĭ
    -0.07
    erre
    -0.07
    stoup
    -0.07
    omu
    -0.07
    vu
    -0.06
    ÑĢей
    -0.06
    جÛĮ
    -0.06
    .onView
    -0.06
    stru
    -0.06
    âĢ¦.↵↵
    -0.06
    POSITIVE LOGITS
    less
    0.18
    lessness
    0.16
    -less
    0.16
    LESS
    0.15
    lessly
    0.13
    以å¤ĸ
    0.13
    -free
    0.12
     olmayan
    0.11
    -Free
    0.09
     less
    0.09
    Activations Density 0.162%

    No Known Activations