© 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. 124427
    Prev
    Next
    INDEX
    Explanations

    indicators of emotional experiences and relationships

    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
    ÃĹ↵↵
    -0.08
     ÄĮer
    -0.07
    ngo
    -0.07
    poÄį
    -0.07
    roys
    -0.07
    ocos
    -0.07
     Ea
    -0.07
    poÄįet
    -0.07
    [__
    -0.07
    úc
    -0.07
    POSITIVE LOGITS
     yeah
    0.06
     (?)
    0.06
    620
    0.06
    uh
    0.06
    0.06
     sondern
    0.06
    vida
    0.06
     ##
    0.06
     Reader
    0.05
     Hend
    0.05
    Activations Density 0.042%

    No Known Activations