© 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 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. 20104
    Prev
    Next
    INDEX
    Explanations

    elements related to discomfort or repulsion

    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
     Paperback
    -0.13
    olis
    -0.13
    ãĥ³ãĥĸ
    -0.12
    าà¸ķร
    -0.12
    .plist
    -0.12
    \Framework
    -0.12
    ä¼ı
    -0.12
    łģ
    -0.12
    SKU
    -0.11
    ÙģتÙĩ
    -0.11
    POSITIVE LOGITS
     pictures
    0.69
     photos
    0.65
     picture
    0.65
     photo
    0.64
     pics
    0.60
     photographs
    0.59
     images
    0.58
     photograph
    0.57
     image
    0.56
     foto
    0.54
    Activations Density 0.234%

    No Known Activations