© 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 EvalsExportsinterp-engineNEWAPI 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. 81101
    Prev
    Next
    INDEX
    Explanations

    references to specific television networks or broadcasting terminology

    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
    pard
    -0.08
    osg
    -0.08
    rist
    -0.08
    lav
    -0.08
    سÙĪب
    -0.07
    rons
    -0.07
    estre
    -0.07
    NameValuePair
    -0.07
    iw
    -0.07
    ulty
    -0.07
    POSITIVE LOGITS
     RT
    0.07
     Carn
    0.06
    537
    0.06
     вз
    0.06
    Ñĩ
    0.06
    RT
    0.06
    ucks
    0.06
     THR
    0.06
    zan
    0.06
     tiên
    0.06
    Activations Density 0.008%

    No Known Activations