© 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. 57381
    Prev
    Next
    INDEX
    Explanations

    expressions related to planning and setting priorities

    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
    bourg
    -0.07
    raÄį
    -0.07
     Kür
    -0.07
    tember
    -0.07
    anship
    -0.07
    /stats
    -0.07
    kode
    -0.06
    omik
    -0.06
    ekim
    -0.06
    ÑĢап
    -0.06
    POSITIVE LOGITS
     list
    0.08
     nhu
    0.08
     specification
    0.08
     requirements
    0.08
     specifications
    0.07
    requirements
    0.07
     requests
    0.07
     Goals
    0.07
     goals
    0.07
     Requests
    0.07
    Activations Density 0.098%

    No Known Activations