Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 18-LLAMASCOPE-RES-32K
    6. 2634
    Prev
    Next
    INDEX
    Explanations

    references to artificial intelligence and robotics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usz
    -0.18
    avir
    -0.16
    UF
    -0.16
    <quote
    -0.15
    rides
    -0.15
    ivy
    -0.14
     पà¤ķ
    -0.14
    klady
    -0.14
    usses
    -0.14
    ride
    -0.14
    POSITIVE LOGITS
     Memory
    0.20
     programmed
    0.19
     humanoid
    0.19
    MEMORY
    0.19
     programming
    0.18
     AI
    0.18
     factory
    0.18
     memory
    0.18
     vat
    0.18
     manufacturing
    0.17
    Activations Density 0.059%

    No Known Activations