© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 17965
    Prev
    Next
    INDEX
    Explanations

    geographical locations and place names

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    èĩ
    -0.14
    æ¼ı
    -0.14
    ittest
    -0.13
    ldb
    -0.13
    大人
    -0.13
     Cohen
    -0.13
    rente
    -0.13
     sca
    -0.13
     ling
    -0.12
    GUID
    -0.12
    POSITIVE LOGITS
     Township
    0.27
     Junction
    0.23
     Heights
    0.23
     township
    0.22
     Mills
    0.22
     tw
    0.21
     Village
    0.20
     heights
    0.20
    -height
    0.20
     Estates
    0.20
    Activations Density 0.179%

    No Known Activations