© 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. 121303
    Prev
    Next
    INDEX
    Explanations

    references to the UK and its citizens or entities in a global context

    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
    ilyn
    -0.07
    lee
    -0.06
    rog
    -0.06
    Via
    -0.06
    vertiser
    -0.06
    uku
    -0.06
     Guest
    -0.06
    meden
    -0.06
     Courtesy
    -0.06
    iddi
    -0.06
    POSITIVE LOGITS
     기ì¤Ģ
    0.09
    -region
    0.08
     region
    0.07
     citizens
    0.07
     domic
    0.07
    ActionCreators
    0.07
     locales
    0.07
    region
    0.07
    ERN
    0.07
     nationals
    0.07
    Activations Density 0.021%

    No Known Activations