© 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. 25-LLAMASCOPE-RES-32K
    11. 18704
    Prev
    Next
    INDEX
    Explanations

    references to quotes and citations in text

    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
    جاÙĨ
    -0.15
    çı
    -0.14
    zahl
    -0.14
    á»ĩn
    -0.14
    ắc
    -0.13
    说æĺİ
    -0.13
    ษ
    -0.13
    enberg
    -0.12
    iza
    -0.12
    ãĥĢãĥ¼
    -0.12
    POSITIVE LOGITS
     quote
    0.83
     quotes
    0.81
     quotation
    0.77
     quoted
    0.75
     quotations
    0.74
    Quote
    0.72
     Quote
    0.72
    quote
    0.71
    -quote
    0.69
     Quotes
    0.69
    Activations Density 0.190%

    No Known Activations