© 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. 105588
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical entities, especially in relation to Israel and Palestine

    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
    åĢĻ
    -0.06
    trace
    -0.06
    OUS
    -0.06
     ÑĩиÑģла
    -0.06
     dist
    -0.06
    iga
    -0.06
     mar
    -0.06
    teen
    -0.05
    ctest
    -0.05
     site
    -0.05
    POSITIVE LOGITS
    -wide
    0.09
    åıĬåħ¶
    0.09
    olik
    0.08
    ians
    0.07
     Airways
    0.07
    asar
    0.07
    anness
    0.07
    -Compatible
    0.07
    (ns
    0.07
     itself
    0.07
    Activations Density 0.034%

    No Known Activations