© 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. 59558
    Prev
    Next
    INDEX
    Explanations

    references to Christianity and associated beliefs

    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
    ents
    -0.07
    sert
    -0.07
    ular
    -0.07
    hin
    -0.07
    á»Ļc
    -0.06
    icular
    -0.06
    elon
    -0.06
    ArgumentException
    -0.06
    ert
    -0.06
    人æ°ij
    -0.06
    POSITIVE LOGITS
    -Muslim
    0.10
    ized
    0.08
    å¾Ĵ
    0.08
    like
    0.08
    /sec
    0.07
    zsche
    0.07
    izing
    0.07
    ophe
    0.07
    ischer
    0.07
    kola
    0.07
    Activations Density 0.008%

    No Known Activations