© 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. 89222
    Prev
    Next
    INDEX
    Explanations

    references to the Library of Congress

    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
    ุà¹Ī
    -0.06
    ESIS
    -0.06
    สมà¸ļ
    -0.06
     Miy
    -0.06
    EMENT
    -0.06
    лив
    -0.06
     Lanka
    -0.05
    angen
    -0.05
    imin
    -0.05
    okit
    -0.05
    POSITIVE LOGITS
    .gov
    0.08
    usk
    0.08
    ãĥ¼ãĥª
    0.07
    onical
    0.07
     Libraries
    0.07
    mits
    0.06
    atura
    0.06
    _US
    0.06
    -US
    0.06
    ibraries
    0.06
    Activations Density 0.004%

    No Known Activations