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. 3-LLAMASCOPE-RES-32K
    6. 16446
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical function definitions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iga
    -0.15
    Gatt
    -0.15
    utherford
    -0.14
    ityEngine
    -0.14
    etes
    -0.13
    Ú¯ÛĮ
    -0.13
    arry
    -0.13
    bral
    -0.13
     parenthesis
    -0.13
    adia
    -0.12
    POSITIVE LOGITS
     Fowler
    0.16
    agma
    0.16
    _SHA
    0.14
    azer
    0.14
    TL
    0.14
    ULA
    0.14
    406
    0.14
    اÙĦÙĥ
    0.14
    _FRAMEBUFFER
    0.13
     unconscious
    0.13
    Activations Density 0.016%

    No Known Activations