© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8422
    Prev
    Next
    INDEX
    Explanations

    topics related to comfort and practical issues related to daily tasks

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Nevertheless
    -0.18
    noch
    -0.17
    Anyway
    -0.15
     ê·¸ëŀĺìĦľ
    -0.15
     daher
    -0.15
    kus
    -0.15
    ÏĥÏį
    -0.15
    urre
    -0.15
    åĨµ
    -0.15
    надлеж
    -0.14
    POSITIVE LOGITS
     again
    0.33
    again
    0.30
     Again
    0.30
    Again
    0.27
    ãģĵãĤĮ
    0.21
    è¿Ļä¸Ģ
    0.19
     This
    0.19
     AGAIN
    0.19
     this
    0.18
     ìĿ´ê²ĥ
    0.18
    Activations Density 0.274%

    No Known Activations