© 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. 95491
    Prev
    Next
    INDEX
    Explanations

    information related to hotel services and amenities

    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
    å°¾
    -0.07
    outil
    -0.07
    PHA
    -0.07
    Carrier
    -0.07
     tá»Ń
    -0.06
     Bilim
    -0.06
    rido
    -0.06
    uffman
    -0.06
    allet
    -0.06
    annie
    -0.06
    POSITIVE LOGITS
     raid
    0.07
    ToJson
    0.07
    icher
    0.06
     Raid
    0.06
    mes
    0.06
     Bren
    0.06
    UBLIC
    0.06
    åºĬ
    0.06
    ichern
    0.06
    alla
    0.06
    Activations Density 0.003%

    No Known Activations