© 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. 56553
    Prev
    Next
    INDEX
    Explanations

    references to violence and political protests

    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
    Æł
    -0.07
    umbo
    -0.07
    orth
    -0.07
    endas
    -0.06
     landing
    -0.06
    ulis
    -0.06
    onya
    -0.06
    rel
    -0.06
    ilestone
    -0.06
    landing
    -0.06
    POSITIVE LOGITS
     violence
    0.08
     Civil
    0.07
     violent
    0.07
     civil
    0.07
     law
    0.07
     participant
    0.06
    Inlining
    0.06
     Odin
    0.06
     organizer
    0.06
    heck
    0.06
    Activations Density 0.049%

    No Known Activations