© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 31648
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to satisfaction and completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osman
    -0.17
     Bean
    -0.16
     Fibonacci
    -0.16
     Hudson
    -0.16
    andum
    -0.15
    Bean
    -0.15
     Mandela
    -0.15
     Joanna
    -0.14
     Tub
    -0.14
     Joan
    -0.14
    POSITIVE LOGITS
     Brett
    0.88
     Bret
    0.79
     Britt
    0.56
     Brittany
    0.52
     BRE
    0.51
    rett
    0.48
    Brit
    0.46
     Brent
    0.41
     Gret
    0.39
     Bren
    0.38
    Activations Density 0.014%

    No Known Activations