© 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. 118095
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conflict or controversy in discussions

    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
     elsewhere
    -0.09
    许å¤ļ
    -0.07
     many
    -0.07
     многиÑħ
    -0.07
     everywhere
    -0.07
     throughout
    -0.07
    ضÙĦ
    -0.06
    ãģĻãģ¹ãģ¦
    -0.06
    OTAL
    -0.06
     birçok
    -0.06
    POSITIVE LOGITS
     occasional
    0.12
     occasionally
    0.12
    few
    0.10
     few
    0.10
     thôi
    0.09
     maybe
    0.09
     Occasionally
    0.09
    å°ij
    0.09
     quelques
    0.09
     nothing
    0.09
    Activations Density 0.061%

    No Known Activations