© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94107
    Prev
    Next
    INDEX
    Explanations

    mentions of amenities and services in accommodations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    neh
    -0.06
     pocket
    -0.06
     Tome
    -0.06
    emmel
    -0.06
     orb
    -0.06
     oc
    -0.06
     screen
    -0.05
    lej
    -0.05
     Economy
    -0.05
    titleLabel
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
     tetas
    0.08
    GenerationStrategy
    0.07
    Lint
    0.07
    VERTISEMENT
    0.07
    INET
    0.07
    uba
    0.07
    kus
    0.07
     lesbi
    0.07
    avenport
    0.07
    Activations Density 0.001%

    No Known Activations