© 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. 23-LLAMASCOPE-RES-32K
    11. 29893
    Prev
    Next
    INDEX
    Explanations

    repeated patterns of the substring "qu"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eee
    -0.16
    uction
    -0.16
     Wr
    -0.15
    ॰
    -0.14
     tweet
    -0.14
    اسر
    -0.14
    bsd
    -0.14
    νι
    -0.14
     Proud
    -0.14
    cela
    -0.14
    POSITIVE LOGITS
    ilibrium
    0.20
    adr
    0.20
    ette
    0.20
    attro
    0.20
    inox
    0.19
    itect
    0.19
    NavController
    0.18
    artz
    0.18
    aternion
    0.17
    croft
    0.17
    Activations Density 0.026%

    No Known Activations