© 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. 20-LLAMASCOPE-RES-32K
    11. 12940
    Prev
    Next
    INDEX
    Explanations

    references to farming and agricultural education programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ityEngine
    -0.15
    õi
    -0.14
     fuss
    -0.14
     porte
    -0.13
    antino
    -0.13
    fik
    -0.13
    Cities
    -0.13
    azer
    -0.13
     Cities
    -0.13
     needle
    -0.13
    POSITIVE LOGITS
     farm
    0.45
     farms
    0.41
    farm
    0.38
     farming
    0.38
     Farm
    0.34
     agriculture
    0.34
     ranch
    0.33
     agricultural
    0.33
     farmers
    0.32
     Agriculture
    0.32
    Activations Density 0.388%

    No Known Activations