© 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. 60459
    Prev
    Next
    INDEX
    Explanations

    references to power struggles and conflicts within political contexts

    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
     Maryland
    -0.08
     Texas
    -0.07
     Virginia
    -0.07
     Colorado
    -0.07
     Kentucky
    -0.06
     Haiti
    -0.06
     Missouri
    -0.06
     Canadian
    -0.06
     Canada
    -0.06
    305
    -0.06
    POSITIVE LOGITS
     Tolkien
    0.13
    olkien
    0.10
     Auckland
    0.09
    .nz
    0.09
    NZ
    0.08
     NZ
    0.08
    elves
    0.08
    agrid
    0.07
     hob
    0.07
    oldur
    0.07
    Activations Density 0.038%

    No Known Activations