© 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. 86413
    Prev
    Next
    INDEX
    Explanations

    phrases related to guided tours and organized activities

    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
    undry
    -0.09
    kah
    -0.07
    akis
    -0.07
    enek
    -0.07
    ãĤ»ãĥ³
    -0.07
    umper
    -0.07
    aska
    -0.07
    ÑĤаб
    -0.07
    ENE
    -0.06
    orns
    -0.06
    POSITIVE LOGITS
     led
    0.07
    Ļ¨
    0.07
     tour
    0.07
    ecom
    0.06
    947
    0.06
    -led
    0.06
    led
    0.06
     tours
    0.06
    ount
    0.06
    929
    0.06
    Activations Density 0.006%

    No Known Activations