© 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 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. 17-LLAMASCOPE-RES-131K
    11. 88737
    Prev
    Next
    INDEX
    Explanations

    references to philosophical concepts and discussions regarding morality and justice

    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
     Fres
    -0.07
    lucent
    -0.07
    zas
    -0.07
    abee
    -0.06
    Transparent
    -0.06
    .nlm
    -0.06
    oward
    -0.06
    elman
    -0.06
    udded
    -0.06
    nid
    -0.06
    POSITIVE LOGITS
     generations
    0.08
     researchers
    0.07
    research
    0.07
     authors
    0.07
     writers
    0.07
     publications
    0.07
     fanc
    0.07
     tongues
    0.07
     theoret
    0.07
     folk
    0.06
    Activations Density 0.075%

    No Known Activations