© 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. 15-LLAMASCOPE-RES-131K
    11. 26371
    Prev
    Next
    INDEX
    Explanations

    phrases indicating character actions and interactions

    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
    odom
    -0.08
    íĨłíĨł
    -0.07
    Ľå»º
    -0.07
    jeme
    -0.07
    zyst
    -0.07
     Truy
    -0.07
    SpaceItem
    -0.07
    elong
    -0.07
    odata
    -0.07
    omaly
    -0.07
    POSITIVE LOGITS
     Haven
    0.06
     Bubble
    0.06
     random
    0.06
     credits
    0.06
    237
    0.06
     shown
    0.05
    \/\/
    0.05
     Rack
    0.05
    ~/
    0.05
     bubble
    0.05
    Activations Density 0.012%

    No Known Activations