Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17546
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to marketing strategies and techniques

    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
    anta
    -0.15
    ä¼ı
    -0.15
     riff
    -0.15
    ledge
    -0.15
    meli
    -0.14
    lds
    -0.14
    icha
    -0.14
    ']!='
    -0.14
    orsi
    -0.14
     lá»Ļ
    -0.13
    POSITIVE LOGITS
     ho
    0.38
     crane
    0.34
     lifting
    0.32
     lifts
    0.30
     lift
    0.29
     win
    0.29
     boom
    0.29
    lifting
    0.28
     Crane
    0.28
     Ho
    0.27
    Activations Density 0.030%

    No Known Activations