© 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. 11-LLAMASCOPE-RES-32K
    11. 29665
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "pair" and related contexts involving teamwork and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -NLS
    -0.19
    缼
    -0.15
     trá»Ŀi
    -0.14
    anou
    -0.14
    sic
    -0.14
    inci
    -0.14
    uld
    -0.14
    è¯ļ
    -0.14
    ipel
    -0.14
    ift
    -0.14
    POSITIVE LOGITS
     itself
    0.17
    ÑĤен
    0.15
     Aires
    0.15
    alian
    0.14
    otec
    0.14
     Emin
    0.14
    zens
    0.14
    º¼
    0.14
     herself
    0.13
     Tennessee
    0.13
    Activations Density 0.636%

    No Known Activations