© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96710
    Prev
    Next
    INDEX
    Explanations

    concepts related to territorial conflict and settlement expansion

    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
    edo
    -0.07
    loor
    -0.07
    deen
    -0.07
    iff
    -0.07
    llum
    -0.07
    rates
    -0.06
    ær
    -0.06
    Pages
    -0.06
    uish
    -0.06
    iffs
    -0.06
    POSITIVE LOGITS
    warts
    0.07
     Verde
    0.07
    ILT
    0.06
    ardo
    0.06
    isphere
    0.06
    -ID
    0.06
    бе
    0.06
    peare
    0.06
    룡
    0.06
     UIControl
    0.06
    Activations Density 0.005%

    No Known Activations