Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 21217
    Prev
    Next
    INDEX
    Explanations

    components related to building user interfaces and handling graphical elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosa
    -0.17
    ål
    -0.16
    æ¼
    -0.15
    776
    -0.14
    823
    -0.14
    818
    -0.14
    colo
    -0.14
    283
    -0.14
    iant
    -0.14
    ué
    -0.14
    POSITIVE LOGITS
    orex
    0.16
     binh
    0.15
    ControlEvents
    0.15
    ars
    0.15
    chartInstance
    0.15
    ker
    0.14
    WithContext
    0.14
    alloca
    0.14
    mobx
    0.14
     )↵↵↵↵↵↵↵↵
    0.14
    Activations Density 0.038%

    No Known Activations