© 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. 77694
    Prev
    Next
    INDEX
    Explanations

    references to childcare and caregiver qualifications

    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
     @}
    -0.08
     Apprent
    -0.07
    imbus
    -0.07
    iÄĩ
    -0.07
    vro
    -0.07
    ÑĢÑĥ
    -0.07
    alse
    -0.06
     ApplicationException
    -0.06
    daÅŁ
    -0.06
     anonym
    -0.06
    POSITIVE LOGITS
    awner
    0.06
     Gap
    0.06
     recent
    0.06
    usercontent
    0.06
    _rpc
    0.06
     plur
    0.06
    _gap
    0.05
    ç«ĭãģ¦
    0.05
    URITY
    0.05
     currently
    0.05
    Activations Density 0.037%

    No Known Activations