© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    phrases that criticize or express skepticism towards authority or credibility

    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
     Kauf
    -0.07
    że
    -0.07
    ÑĤÑı
    -0.07
    ëĭĪëĭ¤
    -0.07
    âĩ
    -0.06
    ickerView
    -0.06
    ŀ
    -0.06
    utsch
    -0.06
    inning
    -0.06
    пион
    -0.06
    POSITIVE LOGITS
     toilet
    0.07
     simplest
    0.07
    dog
    0.07
    ervo
    0.06
     darkest
    0.06
     dog
    0.06
    avenport
    0.06
    =\"#
    0.06
     bathroom
    0.06
     Lowest
    0.06
    Activations Density 0.041%

    No Known Activations