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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119476
    Prev
    Next
    INDEX
    Explanations

    phrases related to promptness and urgency in responses or actions

    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
    _compat
    -0.07
    elop
    -0.07
    .DropDown
    -0.07
    doctrine
    -0.06
    .easing
    -0.06
    ÑģÑıÑĤ
    -0.06
    acy
    -0.06
     ØŃسب
    -0.06
    ,âĢ¦↵↵
    -0.06
    ÙĦØ·
    -0.06
    POSITIVE LOGITS
     nÃło
    0.07
    roken
    0.07
     apparent
    0.07
    aneously
    0.07
     fully
    0.07
    ÑĤаб
    0.07
     sight
    0.06
    gov
    0.06
    udder
    0.06
     Moreno
    0.06
    Activations Density 0.001%

    No Known Activations