© 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. 5-LLAMASCOPE-RES-131K
    11. 126996
    Prev
    Next
    INDEX
    Explanations

    construction-related terms and structures

    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
    ivate
    -0.07
    DIRECTORY
    -0.06
    ãģªãģĮ
    -0.06
    kova
    -0.06
    ãģıãģł
    -0.06
    _bind
    -0.06
    ãģ¾ãĤĭ
    -0.06
    UX
    -0.06
     Establishment
    -0.06
    ãĥ¼ãĤ¹
    -0.06
    POSITIVE LOGITS
    ç½²
    0.07
    reeze
    0.07
    ordable
    0.06
    fak
    0.06
    Brains
    0.06
    μβ
    0.06
     Andrews
    0.06
    би
    0.06
    crest
    0.06
     Rays
    0.06
    Activations Density 0.002%

    No Known Activations