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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 18808
    Prev
    Next
    INDEX
    Explanations

    keywords related to political events and conflicts involving prominent figures or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olt
    -0.15
    oufl
    -0.14
     Bias
    -0.14
     trục
    -0.14
    azzi
    -0.14
    tera
    -0.14
    تاÙĨ
    -0.13
    ÑĢел
    -0.13
    rowse
    -0.13
    ula
    -0.13
    POSITIVE LOGITS
     duk
    0.35
     squared
    0.32
     face
    0.32
     duke
    0.31
     spar
    0.31
     square
    0.30
     compete
    0.30
     faces
    0.28
     faced
    0.27
     engage
    0.26
    Activations Density 0.150%

    No Known Activations