© 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. 17-LLAMASCOPE-RES-131K
    11. 60583
    Prev
    Next
    INDEX
    Explanations

    instances of emotional expressions and hopefulness

    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
    @js
    -0.07
    izu
    -0.07
     agon
    -0.07
    izo
    -0.06
    ÑĢави
    -0.06
    _internal
    -0.06
    acht
    -0.06
     local
    -0.06
     ap
    -0.06
    Stopped
    -0.06
    POSITIVE LOGITS
    uluk
    0.08
     meis
    0.07
    asz
    0.07
    posable
    0.07
    appy
    0.07
    ickerView
    0.07
    Cit
    0.06
     semiclass
    0.06
    ÏĦει
    0.06
    onde
    0.06
    Activations Density 0.000%

    No Known Activations