© 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. 30-LLAMASCOPE-RES-32K
    11. 18772
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and classes in a context of coding or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clayton
    -0.17
    tility
    -0.15
     Clifford
    -0.15
    anzi
    -0.14
    ạng
    -0.14
    Chicago
    -0.14
     Lake
    -0.14
     Clay
    -0.14
     Cin
    -0.13
     Chicago
    -0.13
    POSITIVE LOGITS
     context
    1.19
    context
    1.09
     Context
    1.05
    Context
    0.97
    -context
    0.96
    .context
    0.94
     contexts
    0.94
    _context
    0.93
     CONTEXT
    0.88
    /context
    0.86
    Activations Density 0.368%

    No Known Activations