© 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. MLP
    9. 12-LLAMASCOPE-MLP-32K
    llama3.1-8b · 12-llamascope-mlp-32k
    Source from llama-scope · MLP · Layer 12
    Jump to Source/SAE
    Jump to Feature
    INDEX

    Configuration

    fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L12M-8x
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_mlp_out
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu

    Search Explanations

    Browse

    Features in LLAMA3.1-8B@12-llamascope-mlp-32k
    1. Hover over a feature on the left to preview its details.
    2. Click a feature to lock it and interact with it.