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. 254
    Prev
    Next
    INDEX
    Explanations

    phrases related to predictions and statistical data analysis involving sports teams

    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
    â̦the
    -0.14
    â̦it
    -0.12
     Giải
    -0.12
    â̦and
    -0.11
    .dataTables
    -0.11
    LARI
    -0.10
     Ãľl
    -0.10
    ÌĤ
    -0.10
    [d
    -0.10
    â̦but
    -0.10
    POSITIVE LOGITS
    \Blueprint
    0.12
    hread
    0.12
    lah
    0.11
    _Private
    0.11
     gelmiÅŁ
    0.11
     addCriterion
    0.11
     é¦ĸ页
    0.11
     adultes
    0.10
    .habbo
    0.10
     nonatomic
    0.10
    Activations Density 4.898%

    No Known Activations