© 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. 15-LLAMASCOPE-RES-131K
    6. 62393
    Prev
    Next
    INDEX
    Explanations

    mentions of global issues, especially related to poverty and water crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text elements at the end of content blocks that serve as metadata or content separators, including author attribution, publication dates, and category tags.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Helm
    -0.06
    ções
    -0.06
    581
    -0.06
    ish
    -0.05
    inging
    -0.05
     gal
    -0.05
    415
    -0.05
    å¹ķ
    -0.05
    ocracy
    -0.05
    -re
    -0.05
    POSITIVE LOGITS
    ãİ
    0.08
    ilen
    0.08
     chó
    0.08
    luv
    0.08
    rema
    0.08
    istrovstvÃŃ
    0.07
    voÅĻ
    0.07
    qli
    0.07
    icode
    0.07
    /XMLSchema
    0.07
    Activations Density 0.032%

    No Known Activations