© 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. 31-LLAMASCOPE-RES-32K
    11. 1413
    Prev
    Next
    INDEX
    Explanations

    structured programming syntax elements and delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.16
     tolua
    -0.15
    .*;↵↵
    -0.15
    ucha
    -0.15
     åIJįçĦ¡ãģĹ
    -0.14
    ».↵↵
    -0.14
    @brief
    -0.14
    //
    -0.14
    using
    -0.13
    .portal
    -0.13
    POSITIVE LOGITS
    ↵↵
    1.02
    ↵
    0.71
    ↵↵↵
    0.56
    ↵            ↵
    0.49
    ↵  ↵
    0.44
    č↵
    0.43
    ↵ ↵
    0.40
    ↵                ↵
    0.40
    ↵↵↵↵
    0.39
    ↵    ↵
    0.38
    Activations Density 0.094%

    No Known Activations