© 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. 17-LLAMASCOPE-RES-131K
    11. 128840
    Prev
    Next
    INDEX
    Explanations

    terms related to regional organizations and agreements, particularly those involving ASEAN

    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
    ãģ°ãģĭãĤĬ
    -0.08
    Ïħκ
    -0.08
    دÙĪاج
    -0.08
    ãģĵãģ¡ãĤī
    -0.07
    بÛĮÙĨÛĮ
    -0.07
    ÑĢÑĸд
    -0.07
    ãģ¨ãģĵãĤį
    -0.07
    $__
    -0.07
    .tt
    -0.07
    TEGER
    -0.07
    POSITIVE LOGITS
    s
    0.07
    ardy
    0.07
    ustomed
    0.06
    alian
    0.06
    _makeConstraints
    0.06
    su
    0.06
    H
    0.06
    eah
    0.06
     Edison
    0.06
    js
    0.05
    Activations Density 0.028%

    No Known Activations