© 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. 107517
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical landmarks and cultural heritage

    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
    icros
    -0.07
    endez
    -0.06
    nodeName
    -0.06
     tents
    -0.06
    agara
    -0.06
     farmhouse
    -0.06
    ampa
    -0.06
    æĤł
    -0.06
    wnd
    -0.06
     airports
    -0.06
    POSITIVE LOGITS
     inside
    0.07
    lingen
    0.07
     displays
    0.07
    bite
    0.07
     nich
    0.07
    åĨħéĥ¨
    0.07
     visitor
    0.06
    UDO
    0.06
    충
    0.06
    -spin
    0.06
    Activations Density 0.015%

    No Known Activations