© 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. 16-LLAMASCOPE-RES-32K
    11. 8157
    Prev
    Next
    INDEX
    Explanations

    references to specific artistic works and crafts, particularly ceramics and pottery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ²¹
    -0.18
     Oil
    -0.18
     oil
    -0.17
    iamond
    -0.15
     oily
    -0.15
     Cotton
    -0.15
     oils
    -0.14
    ANCH
    -0.14
     dầu
    -0.14
    aul
    -0.14
    POSITIVE LOGITS
     Fired
    0.24
     clay
    0.23
     fired
    0.22
     pottery
    0.21
    -fired
    0.21
     sứ
    0.20
     firing
    0.20
     гли
    0.19
     Clay
    0.17
    washer
    0.17
    Activations Density 0.065%

    No Known Activations