© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89375
    Prev
    Next
    INDEX
    Explanations

    instances of significant events or developments in life stories

    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
    abs
    -0.07
    arth
    -0.07
     Wich
    -0.06
     Lomb
    -0.06
     serg
    -0.06
     ÐĿаÑģ
    -0.06
    INU
    -0.06
     Universe
    -0.06
     Jeans
    -0.06
    048
    -0.06
    POSITIVE LOGITS
     called
    0.07
    ermo
    0.07
    rawer
    0.07
    ento
    0.07
    called
    0.06
    acco
    0.06
    endor
    0.06
    istani
    0.06
     gá»įi
    0.06
     Fab
    0.06
    Activations Density 0.019%

    No Known Activations