© 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. 28-LLAMASCOPE-RES-32K
    11. 30066
    Prev
    Next
    INDEX
    Explanations

    instances of the word "using" in various contexts, particularly in technical or programming-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vé
    -0.18
    JNI
    -0.17
    ä¿
    -0.15
    rek
    -0.14
    XHR
    -0.14
    orsch
    -0.14
    esk
    -0.14
     Trap
    -0.13
     auss
    -0.13
    hoff
    -0.13
    POSITIVE LOGITS
     Microsoft
    0.24
     namespace
    0.23
    Microsoft
    0.20
     System
    0.19
    namespace
    0.18
     UnityEngine
    0.17
     PropertyChanged
    0.17
    NAMESPACE
    0.16
     Newtonsoft
    0.16
     Orchard
    0.16
    Activations Density 0.015%

    No Known Activations