© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-LLAMASCOPE-RES-32K
    11. 3853
    Prev
    Next
    INDEX
    Explanations

    structured information related to web pages and server data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Designs
    -0.26
    Projects
    -0.26
     Projects
    -0.25
    projects
    -0.25
     Programs
    -0.24
     Models
    -0.23
    _models
    -0.22
    Models
    -0.22
    programs
    -0.21
    udies
    -0.21
    POSITIVE LOGITS
     edges
    0.42
     columns
    0.41
     corners
    0.41
     lines
    0.40
     bars
    0.39
     nodes
    0.39
     segments
    0.39
     channels
    0.39
     lanes
    0.38
     pillars
    0.37
    Activations Density 0.632%

    No Known Activations