© 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. 9063
    Prev
    Next
    INDEX
    Explanations

    references to organizational processes and teamwork dynamics

    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
    reon
    -0.19
    inds
    -0.15
    ãĥ¼ãĥĭ
    -0.15
    ux
    -0.15
    berapa
    -0.15
    awner
    -0.15
    UX
    -0.14
     afore
    -0.14
    ãĥĨãĥ«
    -0.14
     gerne
    -0.14
    POSITIVE LOGITS
     thereby
    0.38
     thus
    0.33
     Consequently
    0.28
     consequently
    0.28
    thus
    0.26
     Thus
    0.26
    è¿Ļæł·
    0.26
     therefore
    0.25
    Thus
    0.22
     resulting
    0.22
    Activations Density 0.378%

    No Known Activations