© 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. 17-LLAMASCOPE-RES-131K
    11. 74592
    Prev
    Next
    INDEX
    Explanations

    concepts related to industrialization and the labor force

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stem
    -0.08
    eken
    -0.07
    au
    -0.06
    lá
    -0.06
    ami
    -0.06
    UNT
    -0.06
    rou
    -0.06
    wit
    -0.06
    2
    -0.06
    ful
    -0.06
    POSITIVE LOGITS
     itself
    0.09
    /Peak
    0.09
    GMEM
    0.08
    à¹ģละà¸ģาร
    0.07
    .CustomButton
    0.07
    IIIK
    0.07
    /Dk
    0.07
    iento
    0.07
    OffsetTable
    0.07
    curacy
    0.07
    Activations Density 0.074%

    No Known Activations