© 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. 15-LLAMASCOPE-RES-131K
    11. 89782
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizing and managing information or tasks

    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
     pronounced
    -0.06
    ::__
    -0.06
    oman
    -0.06
    eda
    -0.06
    -es
    -0.06
    849
    -0.06
    éijij
    -0.05
    ugi
    -0.05
     tariff
    -0.05
    unami
    -0.05
    POSITIVE LOGITS
    лег
    0.08
    .bc
    0.08
    .borrow
    0.08
    (#)
    0.07
    ót
    0.07
    ãĥ¼ãĥIJ
    0.07
    λη
    0.07
    ewitness
    0.06
    ystone
    0.06
     insert
    0.06
    Activations Density 0.003%

    No Known Activations