© 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. 89643
    Prev
    Next
    INDEX
    Explanations

    instances of emotional turmoil or distress in the narrative

    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
    zee
    -0.07
    isoft
    -0.07
    _INLINE
    -0.07
    eses
    -0.06
    igne
    -0.06
    essed
    -0.06
    ouro
    -0.06
    озна
    -0.06
     ---------------------------------------------------------------------------↵
    -0.06
    ovich
    -0.06
    POSITIVE LOGITS
    inz
    0.07
     advent
    0.07
     foregoing
    0.06
    IntArray
    0.06
    NCY
    0.06
    sez
    0.06
    undle
    0.06
    coder
    0.06
     ready
    0.06
     waits
    0.06
    Activations Density 0.039%

    No Known Activations