© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 31536
    Prev
    Next
    INDEX
    Explanations

    references to retail stores and shopping experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SHOP
    -0.14
    Numeric
    -0.14
    Ïħν
    -0.14
    ola
    -0.13
    _firestore
    -0.13
    etsy
    -0.13
    _blocking
    -0.13
     ฿
    -0.13
    ScreenState
    -0.13
    lient
    -0.13
    POSITIVE LOGITS
     locations
    0.29
     Locations
    0.27
    .com
    0.25
     Rewards
    0.25
     Outlet
    0.24
    ®
    0.24
    locations
    0.23
     corporate
    0.23
     outlet
    0.23
     outlets
    0.23
    Activations Density 0.119%

    No Known Activations