© 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. 31167
    Prev
    Next
    INDEX
    Explanations

    elements related to wellness and therapeutic treatments

    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
    istrovstvÃŃ
    -0.07
    ecko
    -0.06
    auce
    -0.06
    uguay
    -0.06
     shelter
    -0.06
    iras
    -0.06
    graf
    -0.06
     batches
    -0.06
    ouri
    -0.06
    eturn
    -0.06
    POSITIVE LOGITS
     treatment
    0.07
    VML
    0.06
    elif
    0.06
    ίνεÏĦαι
    0.06
    ysl
    0.06
    ASM
    0.06
    обов
    0.06
    èĢ³
    0.06
     ÃĶ
    0.06
     preced
    0.06
    Activations Density 0.007%

    No Known Activations