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. 29-LLAMASCOPE-RES-32K
    6. 12483
    Prev
    Next
    INDEX
    Explanations

    references to outdated web development practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.15
    scribe
    -0.14
    annotation
    -0.14
    боÑĤ
    -0.14
    onym
    -0.13
    Ñĭл
    -0.13
    culus
    -0.13
    /locale
    -0.13
    umd
    -0.12
    ç°
    -0.12
    POSITIVE LOGITS
     CSS
    0.33
     theme
    0.29
     css
    0.28
     Theme
    0.27
    CSS
    0.26
    .css
    0.26
     themes
    0.25
     styles
    0.25
     design
    0.23
     HTML
    0.23
    Activations Density 0.328%

    No Known Activations