© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-LLAMASCOPE-RES-32K
    11. 30174
    Prev
    Next
    INDEX
    Explanations

    references to refugees and related social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĤ
    -0.14
    åľ³
    -0.14
    ancia
    -0.14
     Garn
    -0.14
    ether
    -0.14
     ìŀ
    -0.14
    _pm
    -0.14
    duto
    -0.13
     DISCLAIM
    -0.13
    ihu
    -0.13
    POSITIVE LOGITS
     refugee
    0.29
     Refugee
    0.28
     refugees
    0.27
     asylum
    0.26
    ylum
    0.24
     Refuge
    0.23
     refuge
    0.23
    Ref
    0.22
     ref
    0.21
    _Ref
    0.21
    Activations Density 0.050%

    No Known Activations