© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 5773
    Prev
    Next
    INDEX
    Explanations

    references to major sporting events and football (soccer) matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اÙĦعÙĦ
    -0.15
    ÑĢаÑħ
    -0.14
    ERGE
    -0.14
    ÙĨاÙħÙĩ
    -0.14
    ABL
    -0.14
    AtA
    -0.14
    xing
    -0.14
    ÑĤÑı
    -0.14
     rfl
    -0.13
     filt
    -0.13
    POSITIVE LOGITS
     tournament
    0.19
    大ä¼ļ
    0.17
     World
    0.16
     Tournament
    0.15
     Group
    0.15
     Mund
    0.15
     penalty
    0.15
    ë¡Ŀ
    0.14
    enburg
    0.14
    Responder
    0.14
    Activations Density 0.119%

    No Known Activations