© 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. 27-LLAMASCOPE-RES-32K
    11. 10472
    Prev
    Next
    INDEX
    Explanations

    words related to safety and suggestions for better practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.31
     длÑı
    -0.23
     untuk
    -0.22
    	for
    -0.21
     για
    -0.21
     pentru
    -0.20
     für
    -0.19
    为
    -0.18
     voor
    -0.18
    for
    -0.18
    POSITIVE LOGITS
     purposes
    0.81
     sake
    0.79
     reasons
    0.42
     purpose
    0.41
     PURPOSE
    0.34
    purpose
    0.32
     reason
    0.31
    pur
    0.30
    Purpose
    0.30
    æĿ¥è¯´
    0.29
    Activations Density 0.674%

    No Known Activations