© 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. 5-LLAMASCOPE-RES-131K
    6. 126891
    Prev
    Next
    INDEX
    Explanations

    names of cruise lines and related vessels

    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
    _framework
    -0.07
    etting
    -0.07
    IRD
    -0.07
    å°¼äºļ
    -0.06
     spun
    -0.06
    .dtd
    -0.06
    spin
    -0.06
    OME
    -0.06
    lfw
    -0.06
    UMB
    -0.06
    POSITIVE LOGITS
     Gol
    0.06
    imar
    0.06
    yclopedia
    0.06
    logan
    0.06
    utherland
    0.06
     Fulton
    0.06
    orz
    0.06
     Brewer
    0.06
     BIOS
    0.06
     åī
    0.06
    Activations Density 0.034%

    No Known Activations