© 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. 118249
    Prev
    Next
    INDEX
    Explanations

    references to flight booking websites and legal services

    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
     Rath
    -0.07
    ìĸ¼
    -0.07
     Soph
    -0.06
    URRE
    -0.06
     Miz
    -0.06
    IntPtr
    -0.06
    .contents
    -0.06
     hier
    -0.06
    onte
    -0.06
     DIE
    -0.06
    POSITIVE LOGITS
    quis
    0.07
    tsky
    0.07
    ters
    0.06
    licity
    0.06
    aken
    0.06
    ergy
    0.06
    _sdk
    0.06
    agem
    0.06
    fen
    0.06
    AQ
    0.06
    Activations Density 0.002%

    No Known Activations