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. 26097
    Prev
    Next
    INDEX
    Explanations

    references to grants, funding, or support for artists and arts organizations

    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
    ufs
    -0.17
     ει
    -0.16
    /misc
    -0.16
    缤
    -0.15
    IMIT
    -0.15
    idar
    -0.15
    ìĨ¡
    -0.14
    Attrs
    -0.14
     Ùħدر
    -0.14
    aty
    -0.14
    POSITIVE LOGITS
     arts
    0.43
     Arts
    0.41
    arts
    0.31
     Artists
    0.25
    artists
    0.24
     artists
    0.24
     Artist
    0.24
     Cultural
    0.23
     artistic
    0.23
     cultural
    0.23
    Activations Density 0.072%

    No Known Activations