© 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. 16-LLAMASCOPE-RES-32K
    11. 1398
    Prev
    Next
    INDEX
    Explanations

    concepts related to authority and power dynamics, particularly in the context of governance and leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zia
    -0.17
    /open
    -0.15
    sse
    -0.14
    794
    -0.14
     Sist
    -0.14
    etter
    -0.14
    ocaly
    -0.14
     RoutedEventArgs
    -0.14
    iant
    -0.13
    illion
    -0.13
    POSITIVE LOGITS
     authority
    0.29
     power
    0.28
     rule
    0.26
     control
    0.24
    authority
    0.24
    power
    0.23
     Power
    0.23
     Authority
    0.22
    /power
    0.21
    (power
    0.21
    Activations Density 0.346%

    No Known Activations