© 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. 88027
    Prev
    Next
    INDEX
    Explanations

    technical references related to programming or data 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
    /GPL
    -0.07
    activex
    -0.07
     simpl
    -0.06
    issing
    -0.06
    ulses
    -0.06
    ournal
    -0.06
    Esc
    -0.06
    adesh
    -0.06
     mouths
    -0.06
     Seed
    -0.06
    POSITIVE LOGITS
     alignment
    0.07
     sizeof
    0.07
     layout
    0.07
     Packing
    0.07
    Aligned
    0.07
    (sizeof
    0.07
    sizeof
    0.07
    shaw
    0.07
    layout
    0.06
     Alignment
    0.06
    Activations Density 0.012%

    No Known Activations