© 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. 31-LLAMASCOPE-RES-32K
    11. 1653
    Prev
    Next
    INDEX
    Explanations

    terms related to marketing and customer engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /fontawesome
    -0.16
    Subsystem
    -0.14
     Sabbath
    -0.14
    -git
    -0.14
    .nih
    -0.14
    inge
    -0.14
     اÙĦÙħص
    -0.14
    bios
    -0.13
    repair
    -0.13
    ofi
    -0.13
    POSITIVE LOGITS
     inventory
    0.30
     DSP
    0.30
     publisher
    0.29
     SSP
    0.28
     publishers
    0.28
    DSP
    0.26
     ad
    0.26
     advertiser
    0.26
     Inventory
    0.25
     impression
    0.25
    Activations Density 0.024%

    No Known Activations