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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5929
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs related to structured data and functionality in software development contexts

    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
    activex
    -0.16
    InnerHTML
    -0.15
    veau
    -0.15
    uya
    -0.14
    ControlEvents
    -0.14
     ResourceBundle
    -0.14
     Bryce
    -0.13
     Infragistics
    -0.13
     zie
    -0.13
    _ajax
    -0.13
    POSITIVE LOGITS
     widget
    0.29
     Flutter
    0.26
     Widgets
    0.26
    .copyWith
    0.26
     Widget
    0.26
     Scaffold
    0.25
     scaffold
    0.25
    widget
    0.25
    Flutter
    0.25
    .dart
    0.25
    Activations Density 0.006%

    No Known Activations