© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-LLAMASCOPE-RES-32K
    11. 15044
    Prev
    Next
    INDEX
    Explanations

    elements related to player transactions and injury reports in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resenter
    -0.16
    esel
    -0.15
    argent
    -0.15
    ÅĽnie
    -0.14
    agan
    -0.14
    _cached
    -0.14
    ervo
    -0.14
    çī©
    -0.14
    isor
    -0.14
    napshot
    -0.14
    POSITIVE LOGITS
     versatile
    0.21
     forward
    0.20
     utility
    0.17
    ummer
    0.17
     multif
    0.15
     reserve
    0.15
     diss
    0.15
     left
    0.15
     dual
    0.14
     Utility
    0.14
    Activations Density 0.052%

    No Known Activations