© 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. 4416
    Prev
    Next
    INDEX
    Explanations

    references to authority, governance, and community organization 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
    arton
    -0.07
    ½æķ°
    -0.07
    baru
    -0.07
     tiled
    -0.07
     cho
    -0.06
    istrovstvÃŃ
    -0.06
     Advisory
    -0.06
    raya
    -0.06
    enchmark
    -0.06
    oltip
    -0.06
    POSITIVE LOGITS
     decisions
    0.10
     authority
    0.10
     decision
    0.10
    decision
    0.09
    authority
    0.09
     Decision
    0.08
     unauthorized
    0.08
    Decision
    0.08
     Authority
    0.08
    SingleNode
    0.08
    Activations Density 0.029%

    No Known Activations