© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 21082
    Prev
    Next
    INDEX
    Explanations

    instances of humor or laughter in the text

    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
    ascar
    -0.15
    erus
    -0.15
    ivre
    -0.14
    еÑĦ
    -0.14
    ÙĦÙĥ
    -0.14
    说è¯Ŀ
    -0.13
    iado
    -0.13
    posable
    -0.13
     letra
    -0.13
    ãģ£ãģ
    -0.13
    POSITIVE LOGITS
     pause
    0.37
    pause
    0.32
     Pause
    0.30
    Pause
    0.29
    _pause
    0.24
     pa
    0.24
    .pause
    0.24
     paused
    0.23
     pauses
    0.23
    _PAUSE
    0.21
    Activations Density 0.099%

    No Known Activations