© 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. 60549
    Prev
    Next
    INDEX
    Explanations

    topics related to political and economic conditions or crises

    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
    allo
    -0.07
    iasi
    -0.06
     Bias
    -0.06
    ITT
    -0.06
    ìľĦìĽIJíļĮ
    -0.06
     nearly
    -0.06
     bias
    -0.06
    仲
    -0.06
    iske
    -0.06
     separ
    -0.06
    POSITIVE LOGITS
    eyond
    0.07
     beyond
    0.07
     prospects
    0.07
    Lesson
    0.07
    akedirs
    0.07
    OMETRY
    0.06
    lique
    0.06
    phinx
    0.06
    eldorf
    0.06
     плаÑģÑĤи
    0.06
    Activations Density 0.050%

    No Known Activations