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

    Neuronpedia

    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. 125036
    Prev
    Next
    INDEX
    Explanations

    actions related to creative expression and artistic endeavors

    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
    ysi
    -0.08
    ula
    -0.07
    hangi
    -0.07
    /misc
    -0.06
    ÅĻes
    -0.06
    138
    -0.06
    424
    -0.06
    ãģ®ãģłãĤįãģĨ
    -0.06
    ела
    -0.06
    mary
    -0.06
    POSITIVE LOGITS
     differently
    0.07
    µ
    0.06
    foy
    0.06
     dap
    0.06
    raith
    0.06
    ahun
    0.06
    ibel
    0.06
    roke
    0.06
    -runner
    0.06
    nost
    0.06
    Activations Density 0.038%

    No Known Activations