© 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. 87986
    Prev
    Next
    INDEX
    Explanations

    terms related to historical decrees and actions taken in governance

    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
    ouve
    -0.06
     Chapters
    -0.06
    avia
    -0.06
     اØ
    -0.05
     Anti
    -0.05
     chapters
    -0.05
    ее
    -0.05
     Aggregate
    -0.05
    anca
    -0.05
    çŃ
    -0.05
    POSITIVE LOGITS
    dated
    0.10
     dated
    0.10
    undry
    0.08
    -signed
    0.08
    upos
    0.07
    ád
    0.07
     ÙħÙĪر
    0.07
     signed
    0.07
    令
    0.07
    ãĤ¤ãĥī
    0.07
    Activations Density 0.025%

    No Known Activations