© 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. 6147
    Prev
    Next
    INDEX
    Explanations

    structures and patterns in programming syntax and code structure

    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
    erner
    -0.16
    lyph
    -0.15
    otos
    -0.15
    idental
    -0.15
     Pole
    -0.14
    une
    -0.14
     ·
    -0.14
     lick
    -0.14
    arella
    -0.13
    ernet
    -0.13
    POSITIVE LOGITS
    adla
    0.17
    ARAM
    0.15
    .annot
    0.14
    aghan
    0.14
    .twig
    0.13
    HEET
    0.13
    odu
    0.13
     >č↵
    0.13
    帯
    0.13
    ù
    0.13
    Activations Density 0.066%

    No Known Activations