© 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. 10-LLAMASCOPE-RES-32K
    11. 30425
    Prev
    Next
    INDEX
    Explanations

    critiques and discussions surrounding socio-economic systems and their impacts on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocha
    -0.17
    panse
    -0.16
    اØŃ
    -0.16
    ereal
    -0.15
    illac
    -0.15
    issen
    -0.14
    ampil
    -0.14
    Äįel
    -0.13
    ,proto
    -0.13
    atal
    -0.13
    POSITIVE LOGITS
     system
    0.21
    system
    0.21
    ystem
    0.19
    -system
    0.19
     systems
    0.18
    systems
    0.17
    /system
    0.17
    _system
    0.17
     SYSTEM
    0.16
    ç³»ç»Ł
    0.16
    Activations Density 0.179%

    No Known Activations