© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92338
    Prev
    Next
    INDEX
    Explanations

    references to conflicts and wars, particularly in the context of the Middle East

    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
    kel
    -0.07
    arious
    -0.06
    ife
    -0.06
     post
    -0.06
    iger
    -0.06
    gies
    -0.05
     INCIDENT
    -0.05
    ắp
    -0.05
    Coder
    -0.05
     Verm
    -0.05
    POSITIVE LOGITS
    GGLE
    0.07
    ÐŁÐļ
    0.07
    ugins
    0.07
    ãĥ«ãĤ¯
    0.07
    _MetaData
    0.07
    ToPoint
    0.07
    -ending
    0.07
    âĸĪâĸĪ
    0.07
    /copyleft
    0.07
    lias
    0.07
    Activations Density 0.044%

    No Known Activations