© 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. 5-LLAMASCOPE-RES-32K
    11. 2036
    Prev
    Next
    INDEX
    Explanations

    programming-related code snippets and functions in the context of data handling and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ursal
    -0.18
     Lup
    -0.16
     ac
    -0.15
    ì§Ī
    -0.14
    svp
    -0.14
    KeyId
    -0.14
     bedside
    -0.14
    .gz
    -0.14
    å»·
    -0.14
     Kamp
    -0.14
    POSITIVE LOGITS
    radan
    0.19
    ëĮ
    0.16
    ãĤ¸ãĥ¥
    0.16
    ILT
    0.14
    cheduler
    0.14
    DeviceInfo
    0.14
    ceptar
    0.13
    à¸±à¸Ľ
    0.13
    ÑĸÑĪ
    0.13
    tü
    0.13
    Activations Density 1.167%

    No Known Activations