© 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. 15-LLAMASCOPE-RES-131K
    6. 62459
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and amenities in hotel-related descriptions

    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
     Mile
    -0.06
     prů
    -0.06
    تÙĤ
    -0.06
    opsis
    -0.06
     SHIPPING
    -0.06
     Bere
    -0.06
    org
    -0.06
     Shipping
    -0.06
    etal
    -0.06
     gang
    -0.06
    POSITIVE LOGITS
    977
    0.08
    ,readonly
    0.08
    alian
    0.07
     !***
    0.06
    adaÅŁ
    0.06
     Gabriel
    0.06
    anford
    0.06
    olithic
    0.06
    837
    0.06
    ceso
    0.06
    Activations Density 0.004%

    No Known Activations