© 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. 22-LLAMASCOPE-RES-32K
    11. 727
    Prev
    Next
    INDEX
    Explanations

    references to economic empowerment and support for businesses in the context of U.S.-Africa relations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    RuleContext
    -0.17
    udeau
    -0.17
     Southampton
    -0.16
    ëıĮ
    -0.15
     Dummy
    -0.15
    iffin
    -0.15
    _blend
    -0.15
     Willie
    -0.14
    reste
    -0.14
    ë¶
    -0.14
    POSITIVE LOGITS
     Fog
    0.18
     Embassy
    0.17
    ead
    0.17
     dv
    0.17
     democracy
    0.16
     embassy
    0.16
     narcotics
    0.15
    еÑı
    0.15
    acs
    0.15
     cables
    0.15
    Activations Density 0.167%

    No Known Activations