© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77071
    Prev
    Next
    INDEX
    Explanations

    expressions related to the consequences of decisions and responsibilities in life

    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
    ongan
    -0.06
    tingham
    -0.06
    uki
    -0.06
    elson
    -0.06
    moire
    -0.06
    вÑĸлÑĮ
    -0.06
    çon
    -0.06
    spiracy
    -0.06
    apolis
    -0.06
    iesen
    -0.06
    POSITIVE LOGITS
    ajs
    0.06
     crem
    0.06
     ÅĻÃŃj
    0.06
     ÑĢÑı
    0.06
     sharedInstance
    0.06
    ë¡Ģ
    0.06
    fieldname
    0.06
     ALOG
    0.06
    à¤ļन
    0.06
    HideInInspector
    0.06
    Activations Density 0.013%

    No Known Activations