© 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. 4360
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases associated with significant events and their impacts

    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
    å¼¥
    -0.08
    знаÑĩ
    -0.07
    iona
    -0.06
    ucus
    -0.06
     steady
    -0.06
    acet
    -0.06
    eros
    -0.06
    ategy
    -0.06
     norge
    -0.06
     vess
    -0.06
    POSITIVE LOGITS
    äºĭ件
    0.07
     event
    0.07
     forever
    0.06
    oldem
    0.06
     influences
    0.06
    oggler
    0.06
     inst
    0.06
    ypse
    0.06
     gal
    0.06
     episode
    0.06
    Activations Density 0.039%

    No Known Activations