© 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. 59287
    Prev
    Next
    INDEX
    Explanations

    references to binge-watching and the impact of streaming services on viewer habits

    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
    uxt
    -0.07
     RADIO
    -0.07
     WARRANT
    -0.07
    .ua
    -0.07
    UGIN
    -0.06
    ÙĪت
    -0.06
    .updateDynamic
    -0.06
     Kiev
    -0.06
    INI
    -0.06
    ATEST
    -0.06
    POSITIVE LOGITS
     Netflix
    0.12
    flix
    0.09
    Netflix
    0.08
    .netflix
    0.08
     Fargo
    0.07
    unga
    0.07
    owan
    0.06
     evangel
    0.06
    etration
    0.06
     Hansen
    0.06
    Activations Density 0.017%

    No Known Activations