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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 24921
    Prev
    Next
    INDEX
    Explanations

    variations and synonyms related to comparisons and similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÂĿ
    -0.18
    oser
    -0.15
    ral
    -0.15
    ãģªãģĬ
    -0.15
    说çļĦ
    -0.15
     etc
    -0.14
    inerary
    -0.13
     frau
    -0.13
    VIOUS
    -0.13
    ãģ¾ãģŁ
    -0.13
    POSITIVE LOGITS
    ough
    0.16
    eten
    0.16
    à¸Ńà¸ĩà¸Īาà¸ģ
    0.16
    å¹»
    0.15
    itten
    0.15
     vez
    0.15
    моÑĤÑĢÑı
    0.15
    æĸ¼
    0.14
    ÑħÑĥ
    0.14
    lieÃŁlich
    0.14
    Activations Density 0.253%

    No Known Activations