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. 25-LLAMASCOPE-RES-32K
    6. 10775
    Prev
    Next
    INDEX
    Explanations

    numerical data related to sports statistics and financial figures

    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
    iert
    -0.15
    isle
    -0.15
    ApplicationContext
    -0.14
    zim
    -0.14
    arga
    -0.14
    egen
    -0.14
    .addRow
    -0.14
     daily
    -0.14
     annual
    -0.13
     Past
    -0.13
    POSITIVE LOGITS
     ap
    0.67
     each
    0.57
    each
    0.52
     Each
    0.45
    Each
    0.44
     EACH
    0.44
     chac
    0.42
    .each
    0.41
     cada
    0.41
    ìĶ©
    0.38
    Activations Density 0.083%

    No Known Activations