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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82654
    Prev
    Next
    INDEX
    Explanations

    concepts related to the nature of artistic creativity and personal connection

    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
    iren
    -0.07
    arcy
    -0.07
    loat
    -0.07
    ieg
    -0.07
    /trunk
    -0.06
    enties
    -0.06
    tridge
    -0.06
    üss
    -0.06
    avic
    -0.06
    loth
    -0.06
    POSITIVE LOGITS
     acquisition
    0.08
     acquired
    0.08
     trainable
    0.08
     acquisitions
    0.07
     acquiring
    0.07
     Acquisition
    0.07
     acquire
    0.07
     artificial
    0.07
     Artificial
    0.06
     trait
    0.06
    Activations Density 0.028%

    No Known Activations