© 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. 86500
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or contemplation

    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
    dings
    -0.06
     Dew
    -0.06
     dyn
    -0.06
    untime
    -0.06
    æk
    -0.06
    mars
    -0.06
    ụ
    -0.06
    йн
    -0.06
    ameleon
    -0.06
    Äįel
    -0.06
    POSITIVE LOGITS
     existed
    0.10
     existence
    0.10
     exist
    0.10
     Exist
    0.09
     exists
    0.09
    Exist
    0.08
    _exist
    0.08
     possible
    0.08
     previously
    0.07
    existence
    0.07
    Activations Density 0.006%

    No Known Activations