© 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. 87006
    Prev
    Next
    INDEX
    Explanations

    themes related to societal issues and the need for unity

    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
    constitutional
    -0.07
     kans
    -0.07
     stre
    -0.06
     Rebellion
    -0.06
    strup
    -0.06
    Ë
    -0.06
    oret
    -0.06
    adem
    -0.06
    éĢ¸
    -0.06
     constitutional
    -0.06
    POSITIVE LOGITS
     peace
    0.09
     Peace
    0.08
     wars
    0.08
     war
    0.08
    peace
    0.08
    Peace
    0.07
     violence
    0.07
    èo
    0.07
     arms
    0.07
     military
    0.07
    Activations Density 0.038%

    No Known Activations