© 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. 79600
    Prev
    Next
    INDEX
    Explanations

    terms related to vacation ownership and hospitality services

    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
    etine
    -0.07
    erton
    -0.07
    -wage
    -0.06
    antine
    -0.06
    ="{!!
    -0.06
     Omn
    -0.06
     αÏĥ
    -0.06
    izen
    -0.06
    ovice
    -0.06
    aur
    -0.06
    POSITIVE LOGITS
     resorts
    0.09
     membership
    0.08
     Membership
    0.08
     resort
    0.07
     Resorts
    0.07
     Resort
    0.07
     Ski
    0.07
     member
    0.07
     Fraction
    0.07
    membership
    0.07
    Activations Density 0.004%

    No Known Activations