© 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. 70480
    Prev
    Next
    INDEX
    Explanations

    phrases or references related to blessings and judgments

    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
    Ä
    -0.07
    ãĤ¡
    -0.06
    iao
    -0.06
    arih
    -0.06
    à¥įà¤ł
    -0.06
    brains
    -0.06
     lev
    -0.06
    ãĥĬãĥ¼
    -0.06
     L
    -0.05
    bl
    -0.05
    POSITIVE LOGITS
     you
    0.18
    ä½ł
    0.14
    you
    0.13
     você
    0.12
     bạn
    0.12
    _you
    0.12
     your
    0.12
     ä½ł
    0.11
     You
    0.11
     YOU
    0.10
    Activations Density 0.015%

    No Known Activations