© 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. 15-LLAMASCOPE-RES-131K
    11. 89893
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate persistence or determination in the face of challenges

    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
    uren
    -0.07
    IB
    -0.07
    ancy
    -0.06
    lama
    -0.06
    rex
    -0.06
    olver
    -0.06
    ظ
    -0.06
    agn
    -0.06
    arkan
    -0.06
    oux
    -0.06
    POSITIVE LOGITS
     myself
    0.08
     them
    0.07
     it
    0.07
     DÄĽ
    0.07
    this
    0.06
     него
    0.06
    WithEmail
    0.06
    plied
    0.06
     him
    0.06
    987
    0.06
    Activations Density 0.033%

    No Known Activations