© 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. 75491
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles

    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
    ék
    -0.07
    zeit
    -0.07
    ções
    -0.07
    âĢ¦↵↵↵
    -0.07
     æĤ
    -0.07
    forge
    -0.07
    quelle
    -0.07
    ео
    -0.07
    ousy
    -0.07
    ção
    -0.07
    POSITIVE LOGITS
     Janeiro
    0.08
    ioxide
    0.07
    /Card
    0.07
    ansson
    0.06
    eper
    0.06
    ëĿ¼íĶ¼
    0.06
    aepernick
    0.06
    .datab
    0.06
     intervening
    0.06
    Ø¡
    0.06
    Activations Density 0.076%

    No Known Activations