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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-LLAMASCOPE-RES-32K
    6. 11056
    Prev
    Next
    INDEX
    Explanations

    measurements and instructions related to assembly or construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mesh
    -0.21
    mesh
    -0.18
     meshes
    -0.17
     Northwestern
    -0.17
     wire
    -0.17
     grill
    -0.16
     Mesh
    -0.15
     lance
    -0.15
    Structured
    -0.15
     welding
    -0.15
    POSITIVE LOGITS
     router
    0.22
    -router
    0.19
     Router
    0.19
     routers
    0.19
     Plane
    0.19
    _router
    0.18
    router
    0.18
    .router
    0.18
     plane
    0.18
    Router
    0.18
    Activations Density 0.018%

    No Known Activations