© 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. 75739
    Prev
    Next
    INDEX
    Explanations

    key indicators of celebrity actions and events related to personal or social causes

    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
    acia
    -0.07
     zoom
    -0.07
    zoom
    -0.07
    ystack
    -0.07
    ữ
    -0.07
    897
    -0.07
    915
    -0.07
    ä¸Ī
    -0.07
     Bund
    -0.06
    ifle
    -0.06
    POSITIVE LOGITS
     Lair
    0.07
     Tome
    0.06
    seo
    0.06
    оÑĪ
    0.06
     rec
    0.06
    ahl
    0.06
    apa
    0.06
    ابر
    0.06
    icity
    0.06
    APA
    0.06
    Activations Density 0.004%

    No Known Activations