© 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. 105740
    Prev
    Next
    INDEX
    Explanations

    key historical events and figures related to revolutions

    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
     polyester
    -0.07
     NATO
    -0.07
     EU
    -0.07
    196
    -0.07
     Reagan
    -0.07
    ieren
    -0.06
     Facebook
    -0.06
    éĮĦ
    -0.06
    uzz
    -0.06
     Go
    -0.06
    POSITIVE LOGITS
    191
    0.08
    192
    0.07
     Há»ĵ
    0.06
     Há»ĵng
    0.06
    ILINE
    0.06
    _delegate
    0.06
     Tmin
    0.06
    è¨
    0.06
    æľºåħ³
    0.06
     Weiss
    0.06
    Activations Density 0.037%

    No Known Activations