© 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. 130836
    Prev
    Next
    INDEX
    Explanations

    references to historical events related to churches and their communities

    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
     âĨĴ↵↵
    -0.07
    é«
    -0.07
    berger
    -0.06
    typeid
    -0.06
    ả
    -0.06
    igure
    -0.06
    Łèĥ½
    -0.06
     Goldberg
    -0.06
    RuleContext
    -0.06
    agen
    -0.06
    POSITIVE LOGITS
     traveling
    0.06
    ilda
    0.06
     regular
    0.06
     dances
    0.06
     drift
    0.06
     improvis
    0.06
     illegally
    0.06
     Primitive
    0.06
    _cfg
    0.06
     Regular
    0.05
    Activations Density 0.009%

    No Known Activations