© 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. 25-LLAMASCOPE-RES-32K
    11. 11135
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and beverages, particularly in social settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foods
    -0.34
     Foods
    -0.32
     Food
    -0.29
     alimentos
    -0.27
     FOOD
    -0.27
     food
    -0.27
    Food
    -0.27
     comida
    -0.26
    foods
    -0.26
    food
    -0.26
    POSITIVE LOGITS
     drink
    0.40
     drinks
    0.34
     Drink
    0.33
     Bever
    0.33
     beverage
    0.32
     beverages
    0.32
     Beverage
    0.30
     Drinks
    0.29
    drink
    0.29
    Drink
    0.28
    Activations Density 0.064%

    No Known Activations