© 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. 16-LLAMASCOPE-RES-32K
    11. 20975
    Prev
    Next
    INDEX
    Explanations

    elements related to public transportation systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mosul
    -0.24
     Norwich
    -0.22
     Brisbane
    -0.20
     Knoxville
    -0.20
     Bristol
    -0.19
     Norfolk
    -0.19
    Liver
    -0.19
     liver
    -0.18
     Mazda
    -0.18
     Liver
    -0.18
    POSITIVE LOGITS
     Dallas
    0.30
    Dallas
    0.27
     Argentine
    0.22
     Buenos
    0.22
     Argentina
    0.22
    .ibm
    0.22
    Argentina
    0.22
     Kazakhstan
    0.22
     Chicago
    0.21
     Illinois
    0.20
    Activations Density 0.492%

    No Known Activations