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. 32706
    Prev
    Next
    INDEX
    Explanations

    concepts related to mental and sensory awareness

    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
    byn
    -0.18
    ghi
    -0.16
     redistribute
    -0.15
    ulis
    -0.15
     Innoc
    -0.15
    metic
    -0.15
    Ãło
    -0.15
    سط
    -0.15
    isphere
    -0.15
     Spect
    -0.14
    POSITIVE LOGITS
    986
    0.18
    Ïĥα
    0.15
    tsx
    0.15
     Bates
    0.14
    ç±
    0.14
     clear
    0.14
    اتÙĩ
    0.14
    essler
    0.14
     ÑıÑģ
    0.14
    borg
    0.14
    Activations Density 0.210%

    No Known Activations