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

    Neuronpedia

    APICircuit 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. 269
    Prev
    Next
    INDEX
    Explanations

    phrases related to dog harnesses and their usage

    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
    AdapterFactory
    -0.15
    Insets
    -0.15
     DependencyProperty
    -0.15
    .opensource
    -0.15
    *>(&
    -0.15
    adoo
    -0.14
     Angiospermae
    -0.14
    ï¼ł
    -0.14
    оÑģÑĢед
    -0.14
    ħį
    -0.14
    POSITIVE LOGITS
     related
    0.26
     image
    0.25
     medium
    0.23
     view
    0.23
     Related
    0.22
     close
    0.19
    image
    0.19
     how
    0.19
    Related
    0.19
     full
    0.18
    Activations Density 0.013%

    No Known Activations