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. MLP
    5. 22-LLAMASCOPE-MLP-32K
    6. 32734
    Prev
    Next
    INDEX
    Explanations

    references to art and coloring activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MSN
    -0.18
    735
    -0.17
    foy
    -0.17
    scheme
    -0.17
    лÑıн
    -0.16
    Scheme
    -0.16
    iete
    -0.15
    á»ī
    -0.15
    vue
    -0.15
    fragistics
    -0.14
    POSITIVE LOGITS
     colour
    0.38
     coloring
    0.33
     Colour
    0.32
     color
    0.32
    color
    0.30
    colour
    0.29
     Color
    0.28
    Color
    0.27
    -color
    0.26
    .color
    0.26
    Activations Density 0.269%

    No Known Activations