© 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. 1744
    Prev
    Next
    INDEX
    Explanations

    words related to fashion and retail

    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
     ÃľNÄ°
    -0.29
     ulaÅŁ
    -0.27
     kurtul
    -0.26
    lardan
    -0.24
    dız
    -0.24
     Yönet
    -0.23
     Uygu
    -0.23
     ÃľNÄ°VERS
    -0.21
    üncü
    -0.21
     Ä°mpar
    -0.21
    POSITIVE LOGITS
     görün
    0.20
     olduÄŁundan
    0.20
     düzenli
    0.20
     sanki
    0.20
     olab
    0.20
     birden
    0.19
     olmasına
    0.19
     gerçekten
    0.19
     imkan
    0.19
     hiç
    0.19
    Activations Density 0.002%

    No Known Activations