© 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. 31-LLAMASCOPE-RES-32K
    11. 5457
    Prev
    Next
    INDEX
    Explanations

    information related to consumer trends and preferences in the health food industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -cols
    -0.15
    ï¼Ŀ
    -0.15
    -sama
    -0.14
     Reservation
    -0.14
     Clothes
    -0.14
     Cloth
    -0.14
    uyo
    -0.14
    icum
    -0.13
     Clothing
    -0.13
    ynchronously
    -0.13
    POSITIVE LOGITS
     reform
    0.22
     attribute
    0.21
     category
    0.20
     portfolio
    0.20
     SKU
    0.20
     innovation
    0.19
     attributes
    0.19
     shelf
    0.19
     SK
    0.19
     sku
    0.19
    Activations Density 0.056%

    No Known Activations