© 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. 88881
    Prev
    Next
    INDEX
    Explanations

    references to creativity, particularly in association with bipolar disorder

    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
     Patch
    -0.07
    ÑģÑĤи
    -0.07
    Messenger
    -0.07
    INY
    -0.06
     Messenger
    -0.06
    istro
    -0.06
    Patch
    -0.06
    èĽ
    -0.06
     rug
    -0.06
    /tiny
    -0.06
    POSITIVE LOGITS
     executive
    0.09
    /exec
    0.08
     Executive
    0.08
     task
    0.07
    attention
    0.07
     gating
    0.07
     attention
    0.07
     Task
    0.07
     Attention
    0.07
    exec
    0.06
    Activations Density 0.012%

    No Known Activations