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. 11-LLAMASCOPE-RES-32K
    6. 977
    Prev
    Next
    INDEX
    Explanations

    concepts related to regulations and legal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antino
    -0.15
    upe
    -0.15
     Kings
    -0.14
    auer
    -0.14
    Cached
    -0.14
    rome
    -0.14
    isphere
    -0.14
    antz
    -0.14
    atters
    -0.14
    elp
    -0.14
    POSITIVE LOGITS
    ori
    0.15
    ILLISE
    0.14
    uada
    0.14
    à¹ģà¸Ĺà¸Ļ
    0.14
    locker
    0.14
    æħİ
    0.14
    orf
    0.14
    à¥įरण
    0.14
    ynet
    0.14
    .gameserver
    0.14
    Activations Density 0.019%

    No Known Activations