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. 241
    Prev
    Next
    INDEX
    Explanations

    concepts related to diversity and representation in various contexts

    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
    éri
    -0.13
    rew
    -0.13
    aked
    -0.13
    uchi
    -0.13
    onth
    -0.13
    ãģ¨ãĤĤ
    -0.12
    ped
    -0.12
     Discount
    -0.12
    indent
    -0.12
    Ç
    -0.12
    POSITIVE LOGITS
     diversity
    0.81
     diverse
    0.65
     Diversity
    0.64
     variety
    0.63
     divers
    0.63
     diversified
    0.53
     Variety
    0.53
     varied
    0.51
     ëĭ¤ìĸij
    0.50
     çeÅŁit
    0.44
    Activations Density 0.515%

    No Known Activations