© 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. 120665
    Prev
    Next
    INDEX
    Explanations

    terms related to stimulation and enhancing positive responses or effects

    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
    quam
    -0.08
    iska
    -0.07
    wy
    -0.07
    ../../../
    -0.07
    esh
    -0.07
    asu
    -0.07
    GER
    -0.07
    à¸Ńà¸ļ
    -0.07
    eming
    -0.07
    lor
    -0.07
    POSITIVE LOGITS
    åĻ¨
    0.08
    -response
    0.08
    ulus
    0.08
    æĿIJ
    0.07
    agma
    0.07
    aneously
    0.07
     Ree
    0.07
     growth
    0.07
    argo
    0.06
    oeff
    0.06
    Activations Density 0.010%

    No Known Activations