© 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. 105643
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of opinions or beliefs, particularly in reference to personal or societal issues

    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
    oui
    -0.07
    ign
    -0.07
    FOUND
    -0.07
    ssi
    -0.07
    argas
    -0.07
    ëĭĿ
    -0.07
    foon
    -0.07
    mainwindow
    -0.07
     quay
    -0.07
    illac
    -0.07
    POSITIVE LOGITS
     correct
    0.07
     bas
    0.07
     speaking
    0.06
     talking
    0.06
     sing
    0.06
    jp
    0.06
     refer
    0.06
     convers
    0.05
     caution
    0.05
     saying
    0.05
    Activations Density 0.030%

    No Known Activations