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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 20997
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to expenses, costs, and economic implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansom
    -0.15
     tiết
    -0.13
    बल
    -0.13
    -FIRST
    -0.13
    ujeme
    -0.13
    emin
    -0.12
    ãģĿãĤĮãģ¯
    -0.12
    ÑĢоÑģÑĤо
    -0.12
    .jd
    -0.12
    ساÙĨÛĮ
    -0.12
    POSITIVE LOGITS
     along
    0.48
     plus
    0.43
     as
    0.43
    along
    0.36
     ainsi
    0.32
    以åıĬ
    0.31
     among
    0.31
     alongside
    0.30
     together
    0.29
     while
    0.29
    Activations Density 0.301%

    No Known Activations