© 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. 59580
    Prev
    Next
    INDEX
    Explanations

    expressions of concern or action related to safety and well-being

    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
    akis
    -0.07
    isko
    -0.07
    구
    -0.07
    __[
    -0.07
    _BANK
    -0.07
    Ñĥнк
    -0.07
    دÙĬ
    -0.07
    äº
    -0.07
    scal
    -0.07
    _Generic
    -0.07
    POSITIVE LOGITS
     welfare
    0.09
     concern
    0.09
     concerns
    0.07
     preocup
    0.07
     concerned
    0.07
     Concern
    0.07
     Sick
    0.07
     Welfare
    0.07
     Wor
    0.06
     whether
    0.06
    Activations Density 0.024%

    No Known Activations