© 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. 20-LLAMASCOPE-RES-32K
    11. 7013
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to financial and economic considerations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    воз
    -0.14
    éra
    -0.13
    orer
    -0.13
    -0.13
     recip
    -0.13
     Mang
    -0.12
    591
    -0.12
    izon
    -0.12
    GetCurrent
    -0.12
    è¬Ľ
    -0.12
    POSITIVE LOGITS
     thought
    0.50
    æĢĿèĢĥ
    0.44
     thinking
    0.44
    thought
    0.44
    think
    0.43
    thinking
    0.43
     THINK
    0.43
     Thought
    0.43
     thoughts
    0.42
     reflection
    0.42
    Activations Density 0.514%

    No Known Activations