© 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. 3031
    Prev
    Next
    INDEX
    Explanations

    phrases depicting complex themes and elements related to storytelling 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
     Washer
    -0.07
    عر
    -0.07
    unic
    -0.06
     Troy
    -0.06
     Products
    -0.06
     Maple
    -0.06
    imple
    -0.06
     Stamford
    -0.05
     products
    -0.05
     Dispose
    -0.05
    POSITIVE LOGITS
     mixture
    0.09
    mix
    0.09
     dose
    0.09
    rawer
    0.09
     mix
    0.08
    Mix
    0.08
     Mix
    0.08
     doses
    0.07
    ÑİÑĢ
    0.07
    _mix
    0.07
    Activations Density 0.057%

    No Known Activations