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. 25-LLAMASCOPE-RES-32K
    6. 252
    Prev
    Next
    INDEX
    Explanations

    technical terms related to wallet functionalities and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stro
    -0.16
     Norris
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.14
    Aud
    -0.14
     Drink
    -0.14
     Craw
    -0.14
    ckett
    -0.14
     Kendrick
    -0.13
    .Pixel
    -0.13
    Au
    -0.13
    POSITIVE LOGITS
     CActive
    0.20
     Lightning
    0.19
     Tor
    0.18
     spends
    0.17
     spending
    0.17
     seg
    0.17
     spend
    0.17
     multis
    0.17
     chain
    0.17
     sat
    0.17
    Activations Density 0.030%

    No Known Activations