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. 32574
    Prev
    Next
    INDEX
    Explanations

    phrases involving the act of coming or going, especially associated with experiences and interactions

    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
    gere
    -0.17
    andas
    -0.17
    daÅŁ
    -0.16
    åģľ
    -0.14
    zn
    -0.14
    593
    -0.14
    ello
    -0.14
    ermal
    -0.14
    ικη
    -0.14
    604
    -0.13
    POSITIVE LOGITS
     away
    0.56
     leave
    0.55
     leaving
    0.53
     Away
    0.49
     Leave
    0.47
     leaves
    0.45
    leave
    0.45
    Leave
    0.45
    away
    0.44
     Leaving
    0.43
    Activations Density 0.358%

    No Known Activations