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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP
    5. 22-LLAMASCOPE-MLP-32K
    6. 32499
    Prev
    Next
    INDEX
    Explanations

    references to gaming and entertainment products

    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
    Ïģά
    -0.16
    _patch
    -0.14
    ousel
    -0.14
    Patch
    -0.14
    .unbind
    -0.14
    agi
    -0.14
    SOURCE
    -0.14
     Picture
    -0.14
     Wend
    -0.14
    pai
    -0.14
    POSITIVE LOGITS
    coin
    0.19
     Brunswick
    0.17
    Coin
    0.16
    _coin
    0.16
     Coin
    0.15
     Imports
    0.15
    .CreateInstance
    0.15
    enco
    0.15
    116
    0.15
     coin
    0.15
    Activations Density 0.305%

    No Known Activations