© 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. 26-LLAMASCOPE-RES-32K
    11. 5937
    Prev
    Next
    INDEX
    Explanations

    structured sections or chapters within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewe
    -0.13
    phin
    -0.13
     consortium
    -0.13
     kia
    -0.13
     ÙħجÙħÙĪع
    -0.13
    thouse
    -0.13
     kurz
    -0.13
    ulk
    -0.12
    rescia
    -0.12
    .stamp
    -0.12
    POSITIVE LOGITS
     chapter
    1.07
     Chapter
    0.96
     chapters
    0.94
    chapter
    0.89
    Chapter
    0.85
     Chapters
    0.81
     CHAPTER
    0.71
    ç«ł
    0.67
    .chapter
    0.67
    CHAPTER
    0.61
    Activations Density 0.181%

    No Known Activations