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. 27-LLAMASCOPE-RES-32K
    6. 11761
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and actions related to software development and project management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otos
    -0.15
    Lua
    -0.14
    arena
    -0.14
     pil
    -0.14
    placement
    -0.14
    .asp
    -0.14
     strokes
    -0.14
    udur
    -0.13
     Tango
    -0.13
     anus
    -0.13
    POSITIVE LOGITS
     pom
    0.35
     Grad
    0.29
    pom
    0.28
     Pom
    0.26
     mv
    0.25
     grad
    0.24
    Grad
    0.24
     groupId
    0.23
     Shade
    0.23
    mv
    0.22
    Activations Density 0.094%

    No Known Activations