© 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 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. 40469
    Prev
    Next
    INDEX
    Explanations

    instances of gratitude or appreciation towards medical personnel

    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
    ãģķãģĦ
    -0.07
    ortal
    -0.07
    qual
    -0.07
    izio
    -0.07
    .scalablytyped
    -0.07
    uhl
    -0.07
    teil
    -0.07
    ittel
    -0.07
    ROUT
    -0.07
    èĩº
    -0.07
    POSITIVE LOGITS
     equipments
    0.08
    sert
    0.07
     splitted
    0.06
     implication
    0.06
    å±Ģ
    0.06
    niÄį
    0.06
    HIP
    0.06
     Starr
    0.06
    ration
    0.06
    ï¼į
    0.05
    Activations Density 0.001%

    No Known Activations