© 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. 17-LLAMASCOPE-RES-131K
    6. 60083
    Prev
    Next
    INDEX
    Explanations

    expressions of physical discomfort and medical distress

    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
    alah
    -0.09
    okie
    -0.07
    rette
    -0.07
    spb
    -0.07
     Fate
    -0.07
    ÑĩаÑĤ
    -0.07
    .yahoo
    -0.07
     nhắc
    -0.07
    illas
    -0.07
    nete
    -0.07
    POSITIVE LOGITS
     Mein
    0.06
     vomiting
    0.05
    971
    0.05
    RefCount
    0.05
    Lesson
    0.05
    -render
    0.05
    arer
    0.05
    980
    0.05
     Jacques
    0.05
    DataContract
    0.05
    Activations Density 0.012%

    No Known Activations