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

    Neuronpedia

    Jacobian LensNEW
    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. 20-LLAMASCOPE-RES-32K
    11. 30104
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional responses and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     xong
    -0.16
    ืà¸Ńà¸ĩ
    -0.15
    ihn
    -0.14
    enser
    -0.14
    تاب
    -0.13
    ãģ«ãģ¨
    -0.12
    endif
    -0.12
    <typeof
    -0.11
    hir
    -0.11
    .kotlin
    -0.11
    POSITIVE LOGITS
     when
    1.12
    when
    0.96
     quando
    0.85
     cuando
    0.84
    	when
    0.80
    _when
    0.78
     When
    0.77
     khi
    0.75
     WHEN
    0.75
    When
    0.74
    Activations Density 1.135%

    No Known Activations