© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 13-LLAMASCOPE-RES-32K
    11. 18363
    Prev
    Next
    INDEX
    Explanations

    phrases related to the promotion and development of cricket as a sport

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chn
    -0.15
    ľ
    -0.14
    xit
    -0.14
    кÑĥп
    -0.14
    adin
    -0.13
    rams
    -0.13
    asl
    -0.13
    ofday
    -0.13
    asco
    -0.13
     Moder
    -0.13
    POSITIVE LOGITS
     development
    0.18
    idot
    0.16
     training
    0.16
     talent
    0.15
     Training
    0.14
    -development
    0.14
     Development
    0.14
     Chop
    0.14
    rut
    0.14
    ãĥ¼ãĥľ
    0.14
    Activations Density 0.020%

    No Known Activations