© 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. 5939
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual pursuits

    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
    ضÛĮ
    -0.19
    GuidId
    -0.17
    ÙģØ´
    -0.15
    ÑĢава
    -0.15
    BitFields
    -0.15
     Feinstein
    -0.15
    udent
    -0.15
    #
    -0.15
    tolua
    -0.14
     NSCoder
    -0.14
    POSITIVE LOGITS
     nov
    0.21
     Abb
    0.18
     mon
    0.17
    Ń
    0.17
     Stations
    0.17
     nun
    0.16
     contempl
    0.16
     n
    0.16
     abb
    0.16
     clo
    0.15
    Activations Density 0.155%

    No Known Activations