© 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. 2962
    Prev
    Next
    INDEX
    Explanations

    the concept of conclusions or resolutions at the end of phrases

    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
    ceed
    -0.07
    outh
    -0.07
    HELL
    -0.06
    -letter
    -0.06
     Letter
    -0.06
    letter
    -0.06
     letter
    -0.06
     ntohs
    -0.06
    Letter
    -0.06
    Ã¤ÃŁ
    -0.06
    POSITIVE LOGITS
    ÑĢоÑģÑĤо
    0.07
    дап
    0.07
    bstract
    0.07
    าà¸į
    0.07
    hone
    0.07
    ieux
    0.07
    ettle
    0.07
    vik
    0.07
    endas
    0.07
    IRST
    0.07
    Activations Density 0.003%

    No Known Activations