© 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. 9-LLAMASCOPE-RES-131K
    11. 98032
    Prev
    Next
    INDEX
    Explanations

    instances of moral decision-making or ethical conduct

    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
    cee
    -0.08
    ossier
    -0.08
    zek
    -0.07
    bil
    -0.06
     Patri
    -0.06
    rip
    -0.06
    rost
    -0.06
     flames
    -0.06
     fron
    -0.06
    esty
    -0.06
    POSITIVE LOGITS
     Trafford
    0.07
    eworld
    0.07
     TERM
    0.06
    yun
    0.06
    æŁĵ
    0.06
    942
    0.06
    Ø·ÙĨ
    0.06
    ÑĸÑĤÑĮ
    0.06
    287
    0.06
    ==============↵
    0.06
    Activations Density 0.000%

    No Known Activations