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. 26085
    Prev
    Next
    INDEX
    Explanations

    topics related to community engagement and social initiatives

    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
    acom
    -0.15
    raya
    -0.14
    asta
    -0.13
     appeals
    -0.13
    ëĭ´
    -0.13
     both
    -0.13
    ère
    -0.13
    offs
    -0.12
    ÎĽ
    -0.12
    Elements
    -0.12
    POSITIVE LOGITS
     locations
    0.28
     stations
    0.26
     sites
    0.24
    locations
    0.22
     Locations
    0.22
     locales
    0.22
     centres
    0.22
     cities
    0.21
     centers
    0.21
     participating
    0.21
    Activations Density 0.402%

    No Known Activations