© 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 EvalsExportsinterp-engineNEWAPI 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. 120741
    Prev
    Next
    INDEX
    Explanations

    sentence endings or punctuation marks

    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
    IIIK
    -0.07
    edii
    -0.07
    essian
    -0.07
    ảng
    -0.06
     YYS
    -0.06
    /UIKit
    -0.06
    sut
    -0.06
    ?family
    -0.06
    /commons
    -0.06
    esel
    -0.06
    POSITIVE LOGITS
     amp
    0.06
    ê¸Ī
    0.06
     DEFINE
    0.06
     fl
    0.06
     ponder
    0.06
    umb
    0.06
    UMB
    0.06
     Technician
    0.06
    ?><
    0.05
     Louise
    0.05
    Activations Density 0.001%

    No Known Activations