© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3808
    Prev
    Next
    INDEX
    Explanations

    concepts related to mental health and the therapeutic benefits of pets

    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
    enth
    -0.07
    rana
    -0.06
    ẵn
    -0.06
    ola
    -0.06
    /UIKit
    -0.06
    ets
    -0.06
    quin
    -0.06
    _Framework
    -0.06
    riminal
    -0.06
     άν
    -0.06
    POSITIVE LOGITS
     reverse
    0.09
     Reverse
    0.07
    strup
    0.07
     particip
    0.07
    udo
    0.07
    reverse
    0.07
     pseudo
    0.07
    Reverse
    0.07
     superf
    0.07
     tzv
    0.07
    Activations Density 0.198%

    No Known Activations