© 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. 19-LLAMASCOPE-RES-32K
    11. 6985
    Prev
    Next
    INDEX
    Explanations

    concepts related to community and commonalities among groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remainder
    -0.17
    .qual
    -0.16
    inci
    -0.15
    ugi
    -0.14
    ku
    -0.14
    ossa
    -0.14
     Haut
    -0.14
    izon
    -0.14
    -NLS
    -0.13
    _iff
    -0.13
    POSITIVE LOGITS
     common
    0.64
     shared
    0.61
    shared
    0.54
    common
    0.52
     Common
    0.49
     Shared
    0.49
    Shared
    0.49
    -shared
    0.48
    -common
    0.47
     COMMON
    0.45
    Activations Density 0.234%

    No Known Activations