© 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. 6-LLAMASCOPE-RES-32K
    11. 2517
    Prev
    Next
    INDEX
    Explanations

    keywords related to sorting and item manipulation in a data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±¥
    -0.16
    izza
    -0.15
     london
    -0.14
    欣
    -0.14
    ingo
    -0.14
    ÑĥмÑĥ
    -0.14
    оба
    -0.14
    velt
    -0.14
     Gall
    -0.14
    London
    -0.14
    POSITIVE LOGITS
    ayar
    0.20
    istar
    0.15
    еÑı
    0.15
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    0.15
    Dlg
    0.14
    ableObject
    0.14
    nar
    0.14
    ãĤ´ãĥª
    0.14
    DOG
    0.14
     Blur
    0.14
    Activations Density 0.035%

    No Known Activations