© 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. 39746
    Prev
    Next
    INDEX
    Explanations

    themes of communal activities and emotional expression

    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
    okud
    -0.07
    kara
    -0.07
    arra
    -0.07
    igham
    -0.07
    alon
    -0.06
     itemprop
    -0.06
    arshal
    -0.06
    arro
    -0.06
    ofil
    -0.06
    bread
    -0.06
    POSITIVE LOGITS
     work
    0.09
     worked
    0.08
     working
    0.08
     ìŀijìĹħ
    0.07
    _Work
    0.07
    Work
    0.07
     Work
    0.07
     Working
    0.07
     Gloves
    0.07
    å·¥ä½ľ
    0.07
    Activations Density 0.021%

    No Known Activations