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. MLP
    5. 22-LLAMASCOPE-MLP-32K
    6. 32498
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "octopus" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chair
    -0.18
     chair
    -0.17
    Chair
    -0.16
     Chair
    -0.15
     Chairs
    -0.15
     Mason
    -0.15
    Inst
    -0.15
    inst
    -0.15
    ãĥªãĥ³ãĤ°
    -0.14
    iaz
    -0.14
    POSITIVE LOGITS
    arus
    0.18
    anner
    0.17
    esson
    0.16
    eam
    0.15
    antis
    0.15
    aned
    0.15
     Zwe
    0.15
    à¥ģà¤Ń
    0.15
    apon
    0.14
    ãĥ³ãĥĢ
    0.14
    Activations Density 0.006%

    No Known Activations