Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 28309
    Prev
    Next
    INDEX
    Explanations

    key elements or significant actions related to community or social aspects in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pre
    -0.14
    stery
    -0.14
    .tech
    -0.14
    ãĥªãĥ³ãĤ°
    -0.14
    ption
    -0.14
    è¯ī
    -0.14
    аÑĢÑĸ
    -0.13
    velope
    -0.13
     preprocess
    -0.13
    _First
    -0.13
    POSITIVE LOGITS
     final
    0.47
    æľĢåIJİ
    0.40
    æľĢå¾Į
    0.39
     ë§Īì§Ģë§ī
    0.38
     finally
    0.38
    final
    0.38
     cuá»iji
    0.38
    -final
    0.36
    Lastly
    0.35
     Lastly
    0.35
    Activations Density 0.002%

    No Known Activations