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. 28-LLAMASCOPE-RES-32K
    6. 23196
    Prev
    Next
    INDEX
    Explanations

    references to citations and authors in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     İnsan
    -0.20
     Düny
    -0.17
    Ãį
    -0.17
     Bölüm
    -0.16
     Bazı
    -0.16
     MÃ¼ÅŁ
    -0.16
     áº
    -0.16
     Onun
    -0.15
     Ãĸzellikle
    -0.15
     İst
    -0.15
    POSITIVE LOGITS
     Oz
    0.24
     Erd
    0.23
    ̧
    0.22
     Dog
    0.22
     Kurt
    0.21
     Alt
    0.21
     Nec
    0.20
     Ser
    0.20
    erdem
    0.20
    orman
    0.20
    Activations Density 0.028%

    No Known Activations