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. 25-LLAMASCOPE-RES-32K
    6. 16483
    Prev
    Next
    INDEX
    Explanations

    references to various artistic and literary elements and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ampp
    -0.15
    ,it
    -0.15
    oyer
    -0.15
    Navigator
    -0.14
    eyer
    -0.14
    EMA
    -0.14
     ÑģÑĤа
    -0.14
    uncios
    -0.13
    asil
    -0.13
    ahoma
    -0.13
    POSITIVE LOGITS
     ê·¸ë¦¬ê³ł
    0.31
    ãģĿãģĹãģ¦
    0.30
    ï¼Į以åıĬ
    0.26
     etc
    0.23
     à¹ģละ
    0.21
    ,and
    0.21
    ï¼ĮæĪĸ
    0.18
    ãĤĪãģ³
    0.18
    ãĢĤãģĿãģĹãģ¦
    0.17
     หร
    0.16
    Activations Density 0.560%

    No Known Activations