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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12-LLAMASCOPE-RES-32K
    6. 28609
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS attributes commonly used in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wner
    -0.15
    é¥
    -0.14
    ichen
    -0.14
    isz
    -0.14
    .bunifuFlatButton
    -0.14
    наÑĩе
    -0.14
    ylim
    -0.14
    blick
    -0.14
     bindActionCreators
    -0.14
    -tank
    -0.13
    POSITIVE LOGITS
     tree
    0.13
     bare
    0.13
    arnation
    0.13
    agues
    0.13
    aren
    0.13
     Tree
    0.13
     Tran
    0.13
    st
    0.13
     Excellence
    0.12
     Sawyer
    0.12
    Activations Density 0.008%

    No Known Activations