© 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. 15-LLAMASCOPE-RES-32K
    6. 32640
    Prev
    Next
    INDEX
    Explanations

    terms related to violent incidents and clashes

    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
    irse
    -0.16
    ammer
    -0.15
    aldi
    -0.15
    alone
    -0.15
    hurst
    -0.14
    .library
    -0.14
    ATA
    -0.14
    á»Ĩ
    -0.14
    uela
    -0.14
     Gener
    -0.14
    POSITIVE LOGITS
    gebn
    0.18
     flashback
    0.16
    ãĤ´ãĥª
    0.15
     sequel
    0.15
    วà¸Ļ
    0.14
     zone
    0.14
    subtype
    0.13
    824
    0.13
    .serializer
    0.13
     zones
    0.13
    Activations Density 0.048%

    No Known Activations