© 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. 17-LLAMASCOPE-RES-131K
    6. 128254
    Prev
    Next
    INDEX
    Explanations

    coding or programming-related structures and elements

    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
    ondo
    -0.06
     Va
    -0.06
    ekil
    -0.06
    коп
    -0.06
     ontvangst
    -0.06
    /cop
    -0.06
    Ãło
    -0.06
    .ncbi
    -0.05
    tz
    -0.05
     ro
    -0.05
    POSITIVE LOGITS
    TestCategory
    0.07
    rawer
    0.07
    ui
    0.07
    enzhen
    0.07
    SingleNode
    0.07
    ÙĪØ±ÙĨ
    0.07
    codegen
    0.07
    é£
    0.06
    edBy
    0.06
    teg
    0.06
    Activations Density 0.008%

    No Known Activations