© 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. 22-LLAMASCOPE-RES-131K
    11. 3850
    Prev
    Next
    INDEX
    Explanations

    references to Christianity and related concepts

    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
    china
    -0.08
    ents
    -0.07
    sert
    -0.07
    gaard
    -0.07
    gest
    -0.07
    eyin
    -0.07
    -China
    -0.07
    urn
    -0.07
    ä¸Ńåįİ
    -0.06
    egin
    -0.06
    POSITIVE LOGITS
    å¾Ĵ
    0.11
    like
    0.10
    ophe
    0.10
    ophobic
    0.08
    opher
    0.08
    -Muslim
    0.07
    ized
    0.07
    ophobia
    0.07
    .GetBytes
    0.07
    iqueta
    0.07
    Activations Density 0.019%

    No Known Activations