© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 13528
    Prev
    Next
    INDEX
    Explanations

    terms related to agricultural and industrial products, particularly emphasizing various raw materials and their associations with production and sustainability issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loc
    -0.17
     bites
    -0.15
     Metals
    -0.15
     metals
    -0.15
    884
    -0.14
    -owned
    -0.14
     incred
    -0.14
    ł
    -0.14
    arde
    -0.13
    anger
    -0.13
    POSITIVE LOGITS
    -processing
    0.25
     production
    0.24
     processing
    0.24
     industry
    0.23
     producers
    0.22
    industry
    0.21
    -production
    0.21
    -producing
    0.21
     producer
    0.21
    production
    0.20
    Activations Density 0.093%

    No Known Activations