© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 682
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions associated with UI interactions and asynchronous operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uchen
    -0.15
    isnan
    -0.15
    aga
    -0.14
    unei
    -0.14
    /licenses
    -0.14
    .getJSONArray
    -0.14
     ()->
    -0.14
    (_:
    -0.14
    Writes
    -0.14
     rop
    -0.14
    POSITIVE LOGITS
    ({↵
    0.35
    ({
    0.32
     ({↵
    0.28
    .apply
    0.27
    .bind
    0.24
    .prototype
    0.23
     ({
    0.22
    =function
    0.22
     [{
    0.22
    .call
    0.22
    Activations Density 0.210%

    No Known Activations