© 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. 27-LLAMASCOPE-RES-32K
    11. 696
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or relationships among different subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .opendaylight
    -0.14
    plorer
    -0.12
    endregion
    -0.12
     Seventh
    -0.11
    abee
    -0.11
    ulg
    -0.11
     Sixth
    -0.10
    ighb
    -0.10
    etri
    -0.10
     IonicModule
    -0.10
    POSITIVE LOGITS
     first
    1.35
    first
    1.19
    .first
    0.91
     FIRST
    0.90
    -first
    0.88
     eerste
    0.87
    	first
    0.86
    _first
    0.85
    (first
    0.83
    First
    0.82
    Activations Density 1.572%

    No Known Activations