© 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. 59881
    Prev
    Next
    INDEX
    Explanations

    references to events, organizational details, or important personnel in a church or community context

    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
     Rever
    -0.08
     religion
    -0.08
     fucked
    -0.08
     religions
    -0.07
     religious
    -0.07
     fuck
    -0.07
     fucking
    -0.07
    fuck
    -0.07
     holy
    -0.07
     Judaism
    -0.07
    POSITIVE LOGITS
     ministry
    0.09
     convict
    0.08
    족
    0.07
     Equip
    0.07
     evid
    0.07
    å¹ķ
    0.07
     relational
    0.07
    equip
    0.07
     ministries
    0.07
     Probe
    0.07
    Activations Density 0.584%

    No Known Activations