© 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. 532
    Prev
    Next
    INDEX
    Explanations

    keywords and terms related to server functionality and management

    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
    ãĥĥãĥĦ
    -0.07
     Oval
    -0.07
    ẻ
    -0.06
    ÄŁan
    -0.06
    ovol
    -0.06
     kube
    -0.06
     Decom
    -0.06
    iali
    -0.06
    -spacing
    -0.06
    681
    -0.06
    POSITIVE LOGITS
    idUser
    0.07
    asio
    0.06
    .googlecode
    0.06
    riel
    0.06
    yg
    0.06
    dish
    0.06
    .io
    0.06
    ania
    0.06
    zh
    0.06
    client
    0.06
    Activations Density 0.011%

    No Known Activations