© 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. 16-LLAMASCOPE-RES-32K
    11. 2444
    Prev
    Next
    INDEX
    Explanations

    terms related to deep-sea diving and its associated risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    619
    -0.17
    vos
    -0.14
     dahi
    -0.14
     Düz
    -0.14
     perimeter
    -0.14
    ulan
    -0.14
    鸣
    -0.14
     dinosaur
    -0.13
     Shore
    -0.13
    Loader
    -0.13
    POSITIVE LOGITS
     bubbles
    0.27
     depths
    0.27
     depth
    0.26
    depth
    0.24
     Depth
    0.23
     Depths
    0.23
    Depth
    0.23
     Bubble
    0.21
     swim
    0.21
     underwater
    0.21
    Activations Density 0.225%

    No Known Activations