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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 11428
    Prev
    Next
    INDEX
    Explanations

    mentions of food and beverages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    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
    -0.38
     Foods
    -0.38
     Food
    -0.35
     FOOD
    -0.34
    foods
    -0.33
     food
    -0.33
    food
    -0.32
    Food
    -0.32
    -food
    -0.31
    _food
    -0.29
    POSITIVE LOGITS
     drink
    0.41
     beverage
    0.32
     Drink
    0.32
     Bever
    0.32
     drinks
    0.31
    drink
    0.30
     beverages
    0.30
     bev
    0.29
     Beverage
    0.28
    Drink
    0.27
    Activations Density 0.047%

    No Known Activations