© 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. 4-LLAMASCOPE-RES-32K
    11. 29973
    Prev
    Next
    INDEX
    Explanations

    references to "gut" and its variations, indicating focus on instinctive or physical reactions and their relevance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awl
    -0.15
    istrovstvÃŃ
    -0.15
    stry
    -0.15
    lite
    -0.14
    екаÑĢ
    -0.14
    forcer
    -0.14
    qrt
    -0.14
    zell
    -0.13
    ibble
    -0.13
    รว
    -0.13
    POSITIVE LOGITS
    ting
    0.18
    achen
    0.18
    ted
    0.15
     Plug
    0.14
    icol
    0.14
     TextAlign
    0.14
    usan
    0.14
    å·¦åı³
    0.14
    ler
    0.14
    chan
    0.14
    Activations Density 0.005%

    No Known Activations