© 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. 15-LLAMASCOPE-RES-32K
    11. 8745
    Prev
    Next
    INDEX
    Explanations

    relational phrases and structures in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONO
    -0.17
    YG
    -0.16
    \grid
    -0.16
    inia
    -0.15
    /REC
    -0.14
    ÅĻÃŃd
    -0.14
    outu
    -0.14
    ewise
    -0.14
    Å¡tÃŃ
    -0.14
    immel
    -0.14
    POSITIVE LOGITS
     three
    0.54
     two
    0.51
     four
    0.41
    three
    0.40
     several
    0.38
     five
    0.36
    two
    0.35
    ä¸ī个
    0.35
    两个
    0.34
     six
    0.33
    Activations Density 0.272%

    No Known Activations