© 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. 24-LLAMASCOPE-RES-32K
    11. 18908
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional experiences and social relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.17
    currently
    -0.16
    PTY
    -0.16
     presently
    -0.15
    ä¸įäºĨ
    -0.15
     Annual
    -0.15
    ÅĽÄĩ
    -0.15
    errick
    -0.14
     annual
    -0.14
    ãģıãĤī
    -0.14
    POSITIVE LOGITS
     throughout
    0.96
     Throughout
    0.78
    Throughout
    0.72
     suá»ijt
    0.52
    à¸ķลà¸Ńà¸Ķ
    0.50
     entire
    0.48
    æķ´ä¸ª
    0.42
     whole
    0.38
     вÑģÑİ
    0.34
     пÑĢоÑĤÑıгом
    0.33
    Activations Density 0.575%

    No Known Activations