© 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. 88070
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to digital rights and legal contexts

    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
    UX
    -0.07
    enan
    -0.06
    olle
    -0.06
    yo
    -0.06
    ux
    -0.06
     Includes
    -0.06
    esser
    -0.06
    /includes
    -0.05
     without
    -0.05
     compared
    -0.05
    POSITIVE LOGITS
     each
    0.15
    each
    0.14
     EACH
    0.13
    åIJĦ
    0.13
     từng
    0.13
     Each
    0.13
    Each
    0.12
    .each
    0.12
     åIJĦ
    0.11
     different
    0.11
    Activations Density 0.002%

    No Known Activations