© 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. 55270
    Prev
    Next
    INDEX
    Explanations

    references to church services and related activities

    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
     pur
    -0.06
    ped
    -0.06
    irit
    -0.06
     scre
    -0.06
     factor
    -0.05
    uls
    -0.05
     od
    -0.05
     P
    -0.05
     pro
    -0.05
    cu
    -0.05
    POSITIVE LOGITS
    oret
    0.08
    ieu
    0.08
    leyin
    0.07
    anske
    0.07
     Decomp
    0.07
    Bindable
    0.07
    uentes
    0.07
    олÑĮно
    0.07
    enti
    0.07
    ioneer
    0.07
    Activations Density 0.007%

    No Known Activations