© 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. 26-LLAMASCOPE-RES-32K
    11. 27614
    Prev
    Next
    INDEX
    Explanations

    instances of the word "originally" and its variations, indicating a focus on the origins or beginnings of concepts, works, or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     already
    -0.20
     still
    -0.19
     currently
    -0.18
     finally
    -0.18
     recently
    -0.18
     soon
    -0.17
     suddenly
    -0.17
     now
    -0.17
     recent
    -0.16
    å·²
    -0.16
    POSITIVE LOGITS
     intended
    0.17
    наÑĩ
    0.17
     conceptual
    0.16
     اÙĦØ£Ùħر
    0.16
     intending
    0.15
     hanya
    0.15
     hedef
    0.15
    ê°ģ
    0.15
    ugas
    0.15
    ìĭľ
    0.14
    Activations Density 0.046%

    No Known Activations