© 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. 83381
    Prev
    Next
    INDEX
    Explanations

    references to the James Bond franchise and its characteristics

    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
     Fri
    -0.07
     Washer
    -0.06
     Hus
    -0.06
    eb
    -0.06
     Ni
    -0.06
     Wilhelm
    -0.06
     Mage
    -0.06
    TL
    -0.06
     Tyson
    -0.06
    iele
    -0.06
    POSITIVE LOGITS
     Bond
    0.10
    007
    0.09
    Bond
    0.09
    ÑĢÑĮ
    0.07
     оÑĩ
    0.07
    Ñıз
    0.07
     Bonds
    0.07
     Thames
    0.07
     shaken
    0.07
     Cannes
    0.07
    Activations Density 0.014%

    No Known Activations