© 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. 89411
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transitions or transformations into different states or conditions

    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
    eview
    -0.07
    atform
    -0.07
    AKE
    -0.07
    à¸Īร
    -0.07
    .crm
    -0.07
    åĬĽ
    -0.06
    ADOR
    -0.06
    .scope
    -0.06
    .Framework
    -0.06
    à¹ģรà¸ĩ
    -0.06
    POSITIVE LOGITS
     relative
    0.07
    gaard
    0.07
    ools
    0.06
     status
    0.06
    arta
    0.06
    837
    0.06
     insign
    0.06
     fits
    0.06
    cpy
    0.06
     abstraction
    0.06
    Activations Density 0.020%

    No Known Activations