© 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. 15-LLAMASCOPE-RES-131K
    11. 87973
    Prev
    Next
    INDEX
    Explanations

    concerns related to mental health issues in educational contexts

    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
    kara
    -0.07
     elemental
    -0.07
    /Typography
    -0.06
    hoff
    -0.06
    foon
    -0.06
    ável
    -0.06
     Elemental
    -0.06
    aub
    -0.06
     Basic
    -0.06
    lict
    -0.06
    POSITIVE LOGITS
     competitive
    0.10
     competitiveness
    0.09
     Competitive
    0.09
    competitive
    0.09
     Pressure
    0.08
    競
    0.08
     pressure
    0.08
     Parents
    0.08
    .parents
    0.07
    Pressure
    0.07
    Activations Density 0.023%

    No Known Activations