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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82596
    Prev
    Next
    INDEX
    Explanations

    topics related to the Israeli-Palestinian conflict and historical narratives surrounding it

    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
    689
    -0.06
     Pend
    -0.06
     recomm
    -0.06
     previously
    -0.06
    èĬĤ
    -0.06
    rolley
    -0.06
    562
    -0.05
    edis
    -0.05
    unn
    -0.05
    &page
    -0.05
    POSITIVE LOGITS
     itself
    0.10
    /DD
    0.08
    uš
    0.08
    /Foundation
    0.07
    /Area
    0.07
    oredProcedure
    0.07
    fé
    0.07
     ÙĪÙħا
    0.07
    ANDOM
    0.07
    endale
    0.07
    Activations Density 0.101%

    No Known Activations