© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80835
    Prev
    Next
    INDEX
    Explanations

    geographic locations, particularly in Asia and China

    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
     scal
    -0.06
    Publication
    -0.06
    oles
    -0.06
    jo
    -0.06
    ipy
    -0.06
    åħµ
    -0.06
    elia
    -0.06
    座
    -0.05
     trap
    -0.05
    Ïģο
    -0.05
    POSITIVE LOGITS
    ityEngine
    0.08
    abilities
    0.07
    /loose
    0.07
    æ³³
    0.07
    uhe
    0.06
    FunctionFlags
    0.06
    ospace
    0.06
    ków
    0.06
    ability
    0.06
    GenerationStrategy
    0.06
    Activations Density 0.001%

    No Known Activations