© 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. 79330
    Prev
    Next
    INDEX
    Explanations

    references to corporate acquisitions and the implications of ownership in the film industry

    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
    ektor
    -0.07
     PartialView
    -0.07
    erce
    -0.07
    ampil
    -0.07
    asics
    -0.07
    alink
    -0.07
    ÑĥÑĪки
    -0.07
    ImageContext
    -0.06
    ylko
    -0.06
    ritz
    -0.06
    POSITIVE LOGITS
    rica
    0.06
     imp
    0.06
     deal
    0.06
     motion
    0.06
    tte
    0.06
    Motion
    0.06
    BUM
    0.06
    icho
    0.06
    ISON
    0.06
     inse
    0.06
    Activations Density 0.002%

    No Known Activations