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. 32490
    Prev
    Next
    INDEX
    Explanations

    information related to financial institutions and credit unions

    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
    ami
    -0.16
    jer
    -0.15
    esser
    -0.14
    marvin
    -0.14
    876
    -0.14
     à¤ļल
    -0.14
    erson
    -0.14
    ани
    -0.13
     Stanley
    -0.13
    ิษ
    -0.13
    POSITIVE LOGITS
    uye
    0.15
     Mage
    0.15
    енка
    0.15
    Mul
    0.15
     Ro
    0.14
    ullan
    0.14
    uali
    0.14
     Aydın
    0.14
    isposable
    0.14
    rych
    0.14
    Activations Density 0.011%

    No Known Activations