© 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. 54927
    Prev
    Next
    INDEX
    Explanations

    terms related to services and amenities provided during events or accommodations

    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
    æľŁ
    -0.06
    irie
    -0.06
     subtree
    -0.06
    ekil
    -0.06
    ParticleSystem
    -0.06
     VÅ©
    -0.06
    han
    -0.06
     McMahon
    -0.06
    NÃį
    -0.05
    ÑĢади
    -0.05
    POSITIVE LOGITS
     purchase
    0.10
     purch
    0.09
     Purchase
    0.09
    _overlay
    0.08
    iken
    0.08
     charge
    0.08
     purchases
    0.08
    Purchase
    0.08
     charges
    0.07
    _purchase
    0.07
    Activations Density 0.016%

    No Known Activations