© 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. 25-LLAMASCOPE-RES-32K
    11. 23125
    Prev
    Next
    INDEX
    Explanations

    total values and counts related to contracts, financial metrics, and population statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tero
    -0.16
    oples
    -0.15
    irez
    -0.15
    kus
    -0.15
    isman
    -0.14
    ieten
    -0.14
    imulator
    -0.14
    Å¡ak
    -0.14
     AssemblyCompany
    -0.14
    'ai
    -0.13
    POSITIVE LOGITS
     ÑģоÑģÑĤавлÑıеÑĤ
    0.35
     ÑģÑĤановиÑĤÑĮ
    0.29
     wyn
    0.26
     equals
    0.23
     is
    0.22
     clocks
    0.20
     equ
    0.19
     hover
    0.19
     ranges
    0.19
     ÑģоÑģÑĤав
    0.19
    Activations Density 0.182%

    No Known Activations