© 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. 85758
    Prev
    Next
    INDEX
    Explanations

    phrases indicating concerns about regulations and their impact during crises

    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
    utschein
    -0.07
    omain
    -0.06
    elage
    -0.06
     moc
    -0.06
    panion
    -0.06
    hub
    -0.06
    _gs
    -0.06
    رش
    -0.05
    rollo
    -0.05
    á»ĭ
    -0.05
    POSITIVE LOGITS
     added
    0.16
     additional
    0.16
    additional
    0.14
     Added
    0.14
     adds
    0.13
     thêm
    0.13
     Additional
    0.12
    added
    0.12
    -added
    0.12
     addition
    0.12
    Activations Density 0.082%

    No Known Activations