© 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. 8-LLAMASCOPE-RES-32K
    6. 30762
    Prev
    Next
    INDEX
    Explanations

    terms related to injuries and physical trauma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bach
    -0.17
    ersh
    -0.17
    erah
    -0.15
    ItemSelected
    -0.14
    bron
    -0.14
    /plugin
    -0.14
     plein
    -0.14
     AXIS
    -0.14
    aki
    -0.14
    олоÑģ
    -0.14
    POSITIVE LOGITS
     Benchmark
    0.17
    asher
    0.17
     Epidemi
    0.16
    Benchmark
    0.16
     Gerard
    0.15
    LOUR
    0.15
    оÑĢд
    0.15
    gii
    0.15
    alog
    0.14
    egov
    0.14
    Activations Density 0.013%

    No Known Activations