© 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. 77613
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and emotional reactions

    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
    readcr
    -0.08
    andex
    -0.07
    exels
    -0.07
    ÏĨο
    -0.07
    wdx
    -0.07
    åĪ»
    -0.07
    کت
    -0.06
    æĶ¹éĿ©
    -0.06
    ControlEvents
    -0.06
    _activities
    -0.06
    POSITIVE LOGITS
    oli
    0.07
    asio
    0.06
    èµı
    0.06
    .gwt
    0.06
    adm
    0.06
     object
    0.06
     appearances
    0.06
    object
    0.06
     interpretation
    0.06
     looks
    0.06
    Activations Density 0.026%

    No Known Activations