© 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. 88007
    Prev
    Next
    INDEX
    Explanations

    references to violence and environmental disasters

    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
    pii
    -0.07
    ätz
    -0.07
    uffers
    -0.07
    gnore
    -0.07
     fik
    -0.07
    oyo
    -0.07
    ä¼Ĺ
    -0.07
     ÑĥлÑĭб
    -0.06
    /place
    -0.06
    azed
    -0.06
    POSITIVE LOGITS
     report
    0.07
    AGAIN
    0.06
     alarm
    0.06
    lament
    0.06
     worry
    0.06
    yh
    0.06
     Alarm
    0.06
     compared
    0.06
     Report
    0.06
     reports
    0.06
    Activations Density 0.023%

    No Known Activations