© 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. 86728
    Prev
    Next
    INDEX
    Explanations

    instances related to tragic incidents or violence

    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
    asti
    -0.07
    armed
    -0.07
    itsu
    -0.07
    usch
    -0.07
    AMPLE
    -0.07
    Ñĩай
    -0.07
    anta
    -0.07
    ested
    -0.07
    onaut
    -0.07
    âĺħâĺħ
    -0.07
    POSITIVE LOGITS
    elu
    0.06
     recently
    0.06
    shade
    0.06
     inse
    0.06
    911
    0.06
    ساب
    0.05
     Cush
    0.05
    _cid
    0.05
     pits
    0.05
     ener
    0.05
    Activations Density 0.011%

    No Known Activations