© 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. 15-LLAMASCOPE-RES-131K
    11. 87100
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions and countries, specifically in Australia and surrounding areas

    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
    ipp
    -0.07
    heimer
    -0.06
    kowski
    -0.06
     Bloss
    -0.06
    avig
    -0.06
    alo
    -0.06
     Tribal
    -0.06
    issant
    -0.06
    ariate
    -0.06
    Navigator
    -0.06
    POSITIVE LOGITS
    ÑĥÑĩа
    0.07
    استاÙĨ
    0.07
    raman
    0.07
    çİĦ
    0.07
     uÄŁ
    0.06
    imen
    0.06
    ानस
    0.06
    ίγ
    0.06
     окÑĤ
    0.06
    phinx
    0.06
    Activations Density 0.002%

    No Known Activations