© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    references to escaping dangerous situations or persecution

    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
    .DOM
    -0.07
    emple
    -0.07
     Furious
    -0.07
    rox
    -0.07
     xuyên
    -0.07
    elmet
    -0.06
    oya
    -0.06
    alm
    -0.06
    rait
    -0.06
    eton
    -0.06
    POSITIVE LOGITS
     hom
    0.07
     persec
    0.07
     persecution
    0.07
    ɵ
    0.07
    ì¦Ŀ
    0.06
     Protection
    0.06
    hores
    0.06
     hot
    0.06
    utschein
    0.06
     SEEK
    0.06
    Activations Density 0.017%

    No Known Activations