© 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. 28-LLAMASCOPE-RES-32K
    11. 20216
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ضاÙĨ
    -0.15
    zial
    -0.14
    ľ
    -0.14
    vere
    -0.14
    449
    -0.14
    ÅĤem
    -0.14
    IfExists
    -0.13
    ieux
    -0.13
    âĶģâĶ
    -0.13
    umber
    -0.13
    POSITIVE LOGITS
     performances
    0.20
     winning
    0.20
     improvement
    0.20
     preparation
    0.20
     win
    0.19
     wins
    0.19
     Improvement
    0.19
     Preparation
    0.18
     elim
    0.17
     perform
    0.17
    Activations Density 0.268%

    No Known Activations