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. 10657
    Prev
    Next
    INDEX
    Explanations

    words related to changes in economic conditions, such as increases, decreases, and trends affecting market dynamics

    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
    isclosed
    -0.16
    adder
    -0.15
    ensely
    -0.15
    macı
    -0.15
    allen
    -0.14
    Ïģι
    -0.14
    urrent
    -0.14
    ween
    -0.14
    باÙĨ
    -0.14
     Rosenstein
    -0.14
    POSITIVE LOGITS
     in
    0.23
    /change
    0.18
     occurring
    0.17
     happening
    0.17
    conde
    0.17
     occurred
    0.16
     seen
    0.16
    746
    0.15
    .getRoot
    0.15
     of
    0.14
    Activations Density 0.140%

    No Known Activations