© 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. 88250
    Prev
    Next
    INDEX
    Explanations

    themes related to emotional struggles and despair

    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
    umo
    -0.07
    tran
    -0.07
    atura
    -0.06
    ÑĢив
    -0.06
    dynamic
    -0.06
    lob
    -0.06
    ikel
    -0.06
    ild
    -0.06
    íĶ¼
    -0.06
    ifo
    -0.06
    POSITIVE LOGITS
     bottom
    0.07
    byss
    0.07
    æĿ
    0.07
    bottom
    0.07
    kontakte
    0.06
    kker
    0.06
     lowest
    0.06
     depression
    0.06
     darkest
    0.06
    Bottom
    0.06
    Activations Density 0.023%

    No Known Activations