© 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. 30564
    Prev
    Next
    INDEX
    Explanations

    concepts related to creativity and artistic expression

    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
    sak
    -0.06
    templ
    -0.06
     cube
    -0.06
    #=
    -0.06
    tp
    -0.06
     khắc
    -0.06
    opo
    -0.06
    ï¼
    -0.06
    713
    -0.05
    tee
    -0.05
    POSITIVE LOGITS
     cycles
    0.09
    ngth
    0.07
    cycles
    0.07
    selectors
    0.07
     cyc
    0.07
     trends
    0.07
    rell
    0.07
     change
    0.07
    change
    0.06
    SYNC
    0.06
    Activations Density 0.032%

    No Known Activations