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. 32426
    Prev
    Next
    INDEX
    Explanations

    elements related to safety and consideration in various contexts

    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
    yn
    -0.16
    ôt
    -0.16
     patron
    -0.15
    INY
    -0.15
    zech
    -0.15
    ım
    -0.15
    expr
    -0.14
    yny
    -0.14
    YN
    -0.14
    stdlib
    -0.14
    POSITIVE LOGITS
     adj
    0.18
    .createObject
    0.15
    OSC
    0.14
     Kick
    0.14
    /per
    0.13
    haps
    0.13
    адки
    0.13
    ishments
    0.13
    .FontStyle
    0.13
    -performance
    0.13
    Activations Density 0.138%

    No Known Activations