© 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. 20-LLAMASCOPE-RES-32K
    11. 24199
    Prev
    Next
    INDEX
    Explanations

    references to leadership positions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nationwide
    -0.23
     nationwide
    -0.22
    åĽ½äº§
    -0.20
    åĽ½åĨħ
    -0.19
    åħ¨åĽ½
    -0.18
     Army
    -0.17
     patriotic
    -0.17
     domestically
    -0.17
     ülkenin
    -0.16
     Midwest
    -0.15
    POSITIVE LOGITS
     global
    0.66
     worldwide
    0.57
    global
    0.56
     Global
    0.54
    Global
    0.50
     globally
    0.49
     world
    0.47
     international
    0.47
     GLOBAL
    0.47
    .global
    0.46
    Activations Density 0.909%

    No Known Activations