© 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. 28012
    Prev
    Next
    INDEX
    Explanations

    amenities and features related to leisure, entertainment, and hospitality settings

    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
    laden
    -0.08
    abouts
    -0.07
    811
    -0.07
    deen
    -0.07
    BOVE
    -0.07
    OrElse
    -0.07
    ipc
    -0.07
    alf
    -0.07
    LETE
    -0.07
    adolu
    -0.07
    POSITIVE LOGITS
     opportunities
    0.06
     facilities
    0.06
     capability
    0.06
     capabilities
    0.06
    èIJ
    0.06
     optical
    0.06
    ież
    0.06
    ži
    0.06
     GOODMAN
    0.06
     opportun
    0.06
    Activations Density 0.033%

    No Known Activations