© 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. 59655
    Prev
    Next
    INDEX
    Explanations

    prominent hotel names and their affiliations in a location

    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
     Oasis
    -0.06
    abi
    -0.06
    acades
    -0.06
    ovich
    -0.05
    thin
    -0.05
    utton
    -0.05
    aminer
    -0.05
    shima
    -0.05
     Composite
    -0.05
    æ²¢
    -0.05
    POSITIVE LOGITS
     
    0.08
     Merk
    0.07
    hev
    0.07
    ære
    0.07
     situated
    0.07
    331
    0.07
    zyst
    0.07
     Offering
    0.07
     Fut
    0.07
    ãĤ¤ãĤº
    0.07
    Activations Density 0.016%

    No Known Activations