© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 4674
    Prev
    Next
    INDEX
    Explanations

    XML or HTML-like syntax elements and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    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
    achs
    -0.15
     Highest
    -0.15
    aghan
    -0.14
    vn
    -0.14
    \helpers
    -0.14
     saf
    -0.14
    ivor
    -0.14
    /modal
    -0.14
    killer
    -0.14
    POSITIVE LOGITS
     è±
    0.14
    æĢ
    0.14
    Enumer
    0.14
    окÑģ
    0.14
    ÏĥοÏħ
    0.14
    leta
    0.14
    ifax
    0.13
    allet
    0.13
    _ADAPTER
    0.13
    ียà¸ģ
    0.13
    Activations Density 0.006%

    No Known Activations