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

    Neuronpedia

    Jacobian LensNEW
    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. 15490
    Prev
    Next
    INDEX
    Explanations

    mentions of physical objects or locations related to experiences or activities

    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
    ارش
    -0.14
    æĸ°çļĦ
    -0.13
    uzzi
    -0.13
    arra
    -0.12
    ekil
    -0.12
    нен
    -0.12
    ycled
    -0.12
    EndPoint
    -0.12
    ÏģÏİν
    -0.12
    geme
    -0.12
    POSITIVE LOGITS
     entire
    1.35
     whole
    1.30
    whole
    1.13
     Entire
    1.02
    æķ´ä¸ª
    0.94
    Whole
    0.93
     Whole
    0.90
     entirety
    0.89
     ganze
    0.73
     hele
    0.66
    Activations Density 0.487%

    No Known Activations