© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41114
    Prev
    Next
    INDEX
    Explanations

    references to accommodations and amenities in a rental property description

    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
    uffer
    -0.07
    ÏĢί
    -0.07
    RELEASE
    -0.06
    IMS
    -0.06
    Æ°á»Ľ
    -0.06
     Lanka
    -0.06
    erts
    -0.06
    äºĭ
    -0.06
     Squ
    -0.06
    agne
    -0.06
    POSITIVE LOGITS
    esian
    0.06
    etak
    0.06
     mutual
    0.06
    dÄĽ
    0.06
    okino
    0.06
    onic
    0.06
     returnUrl
    0.06
     Inputs
    0.06
     Nas
    0.06
    óst
    0.06
    Activations Density 0.001%

    No Known Activations