© 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. 127673
    Prev
    Next
    INDEX
    Explanations

    genres related to film and theater

    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
    APH
    -0.07
    #__
    -0.07
    spb
    -0.07
    еÑĢин
    -0.07
    auge
    -0.07
    ///<
    -0.06
    ниÑĤ
    -0.06
     sund
    -0.06
    mour
    -0.06
    clin
    -0.06
    POSITIVE LOGITS
    athon
    0.07
    /Foundation
    0.07
    261
    0.07
    669
    0.07
    isto
    0.06
    018
    0.06
    ong
    0.06
     |
    0.06
    enko
    0.06
     |↵
    0.06
    Activations Density 0.002%

    No Known Activations