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. 27-LLAMASCOPE-RES-32K
    6. 19279
    Prev
    Next
    INDEX
    Explanations

    references to trade regulations and policies

    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
     beats
    -0.15
    warm
    -0.14
     Fres
    -0.14
    ChildIndex
    -0.14
    725
    -0.14
    estroy
    -0.14
    argas
    -0.14
    ustos
    -0.14
     Fountain
    -0.14
    Ñı
    -0.14
    POSITIVE LOGITS
     WTO
    0.25
     disciplines
    0.23
     Pascal
    0.21
     Members
    0.21
     dispute
    0.20
     WT
    0.20
     Uruguay
    0.19
     Trade
    0.19
    Members
    0.18
     trade
    0.18
    Activations Density 0.044%

    No Known Activations