© 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. 40500
    Prev
    Next
    INDEX
    Explanations

    references to iconic pop culture figures or concepts

    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
    rok
    -0.08
    .viewer
    -0.07
    ismet
    -0.07
    Viewer
    -0.07
    åĻ¨
    -0.07
    ÏĦÏĥ
    -0.07
    sız
    -0.07
    ÑĩеÑģкое
    -0.06
    urd
    -0.06
     Viewer
    -0.06
    POSITIVE LOGITS
     author
    0.08
     creator
    0.08
    .creator
    0.07
    ä½ľèĢħ
    0.07
    creator
    0.07
    oeff
    0.06
     swear
    0.06
    ä»ģ
    0.06
    arrant
    0.06
     maker
    0.06
    Activations Density 0.003%

    No Known Activations