© 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. 56018
    Prev
    Next
    INDEX
    Explanations

    references to television shows and their schedules

    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
    ¯u
    -0.08
    åŃĺäºİ
    -0.08
    esel
    -0.08
    eyin
    -0.07
    anford
    -0.07
    rů
    -0.07
     voks
    -0.07
    Porno
    -0.07
    RESS
    -0.07
    пÑĤом
    -0.07
    POSITIVE LOGITS
     programming
    0.09
     Programming
    0.08
     networks
    0.08
     programs
    0.07
     TV
    0.07
     schedule
    0.07
     schedules
    0.07
     programmes
    0.07
     sched
    0.07
     programmer
    0.07
    Activations Density 0.017%

    No Known Activations