© 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. 15-LLAMASCOPE-RES-131K
    11. 86921
    Prev
    Next
    INDEX
    Explanations

    mentions of hotel names, particularly those associated with the Hilton brand

    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
    letic
    -0.08
    le
    -0.08
    hra
    -0.07
    lem
    -0.07
    gor
    -0.07
    gar
    -0.07
    ë¡ľìĦľ
    -0.07
    ung
    -0.07
    lessly
    -0.07
    annon
    -0.07
    POSITIVE LOGITS
    oids
    0.08
    ssp
    0.07
    ization
    0.07
    opoly
    0.07
    бÑĥÑĢг
    0.07
    elli
    0.07
    eer
    0.07
    bury
    0.07
    ãĤº
    0.07
    alysis
    0.07
    Activations Density 0.033%

    No Known Activations