© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30561
    Prev
    Next
    INDEX
    Explanations

    phrases indicating alertness or concern

    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
    á»ĩ
    -0.08
    .proto
    -0.07
     trụ
    -0.07
     Vie
    -0.07
     Blacks
    -0.07
     Dün
    -0.07
     Bian
    -0.06
    mlink
    -0.06
    AXB
    -0.06
    iko
    -0.06
    POSITIVE LOGITS
     alarm
    0.09
     bells
    0.09
     alert
    0.09
     alarms
    0.09
     alerts
    0.08
     flags
    0.07
    Alarm
    0.07
     bell
    0.07
     Alarm
    0.07
    èѦ
    0.07
    Activations Density 0.030%

    No Known Activations