© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97865
    Prev
    Next
    INDEX
    Explanations

    mentions of the Salvation Army and references to salvation 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
    idot
    -0.07
    addock
    -0.07
    .infinity
    -0.07
     Harness
    -0.07
    ezi
    -0.07
    undler
    -0.07
    Harness
    -0.07
    ãĥ³ãĤ¸
    -0.07
    kovi
    -0.06
    Ý
    -0.06
    POSITIVE LOGITS
    abox
    0.07
    apiKey
    0.06
    INDER
    0.06
    iferay
    0.06
     AABB
    0.06
    .FLAG
    0.06
    itals
    0.06
    RenderingContext
    0.06
    ãĤ±ãĥĥãĥĪ
    0.06
    fig
    0.06
    Activations Density 0.001%

    No Known Activations