© 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 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. 60897
    Prev
    Next
    INDEX
    Explanations

    references to drones in various contexts

    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
    ChangeEvent
    -0.07
    ãģķãģ¾
    -0.07
    avage
    -0.07
    ened
    -0.07
    ä¹ĭä¸Ģ
    -0.06
    ãĥ£
    -0.06
    enos
    -0.06
    åĿĤ
    -0.06
    ifestyles
    -0.06
    aser
    -0.06
    POSITIVE LOGITS
    imal
    0.07
     hovering
    0.07
    ůj
    0.07
    Äįel
    0.07
    /table
    0.07
    /video
    0.07
    insky
    0.07
    翼
    0.07
    ishly
    0.07
    fleet
    0.07
    Activations Density 0.004%

    No Known Activations