© 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. 31-LLAMASCOPE-RES-32K
    11. 30893
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS class attributes and related markup elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.32
     (“
    -0.32
    ["
    -0.31
    __["
    -0.31
    {"
    -0.30
    ["_
    -0.29
    ()["
    -0.28
     "./
    -0.28
     $(".
    -0.28
     {"
    -0.27
    POSITIVE LOGITS
     '
    0.83
     '[
    0.66
     ('
    0.60
     '(
    0.59
     '_
    0.59
     '-
    0.54
     '**
    0.53
     '$
    0.52
     '/
    0.51
     '\
    0.51
    Activations Density 0.413%

    No Known Activations