© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 374
    Prev
    Next
    INDEX
    Explanations

    references to food items and their nutritional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ingredient
    -0.18
    ingredient
    -0.17
    avors
    -0.17
    Ingredients
    -0.16
     Transparent
    -0.16
    esen
    -0.16
     ingredient
    -0.15
     diet
    -0.15
     Ingredients
    -0.15
     waist
    -0.15
    POSITIVE LOGITS
     fruits
    0.29
     nuts
    0.28
     meats
    0.28
     meat
    0.26
     cere
    0.25
     fish
    0.25
     pulses
    0.25
     grains
    0.25
     dairy
    0.24
     diary
    0.24
    Activations Density 0.134%

    No Known Activations