© 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. 124066
    Prev
    Next
    INDEX
    Explanations

    references to home entertainment technology and systems

    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
    setFlash
    -0.07
    Dies
    -0.07
    ниÑĨ
    -0.07
    Platforms
    -0.06
     Dix
    -0.06
     UnityEditor
    -0.06
    -radio
    -0.06
    нÑĮ
    -0.06
    amage
    -0.06
     Shaft
    -0.06
    POSITIVE LOGITS
     Cinema
    0.07
     bez
    0.07
     TV
    0.07
     picture
    0.07
     flick
    0.07
     TVs
    0.07
     edge
    0.07
     television
    0.07
     Picture
    0.07
     display
    0.07
    Activations Density 0.003%

    No Known Activations