© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86908
    Prev
    Next
    INDEX
    Explanations

    phrases related to hotel stays and 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
    902
    -0.07
    gesch
    -0.06
    aine
    -0.06
     Lamp
    -0.06
    antom
    -0.06
    erson
    -0.06
    ame
    -0.06
    Va
    -0.06
    вей
    -0.06
    ile
    -0.05
    POSITIVE LOGITS
    edImage
    0.07
    DataExchange
    0.07
     hotels
    0.07
    itler
    0.07
    overn
    0.07
    endcode
    0.07
    REFERRED
    0.07
    asser
    0.07
    ehr
    0.07
    èĮĤ
    0.07
    Activations Density 0.011%

    No Known Activations