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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 26081
    Prev
    Next
    INDEX
    Explanations

    elements related to life changes and personal struggles

    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
    ãģĹãģ¾ãģĹãģŁ
    -0.19
     recently
    -0.18
     was
    -0.17
    recent
    -0.17
     telah
    -0.16
    was
    -0.16
    Was
    -0.16
     Äijã
    -0.15
    Recently
    -0.15
    ìĽł
    -0.15
    POSITIVE LOGITS
     becomes
    0.30
     begins
    0.23
     blir
    0.22
     gets
    0.22
     wordt
    0.21
     decides
    0.21
     comes
    0.20
     become
    0.20
     receives
    0.20
    ãģ¨ãģªãĤĭ
    0.19
    Activations Density 0.456%

    No Known Activations