© 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. 15-LLAMASCOPE-RES-131K
    11. 86828
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and data processing

    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
    .scalablytyped
    -0.08
    ekim
    -0.07
     обÑĢа
    -0.07
    uchar
    -0.07
    cmds
    -0.07
    eyh
    -0.07
     EXEMPLARY
    -0.07
    FRING
    -0.07
    olu
    -0.06
    Ñıб
    -0.06
    POSITIVE LOGITS
    inge
    0.07
    hus
    0.06
     Mobil
    0.06
    ika
    0.06
    ube
    0.06
    anda
    0.06
    alian
    0.06
    anes
    0.05
    ç«ĭ
    0.05
    æĿ
    0.05
    Activations Density 0.006%

    No Known Activations