© 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. 17-LLAMASCOPE-RES-131K
    11. 79587
    Prev
    Next
    INDEX
    Explanations

    references to places or organizations named "Church" or variations of it

    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
    ãĥ¼ãĥĦ
    -0.06
    eec
    -0.06
    ÑĢаÑģ
    -0.06
    aks
    -0.06
    assen
    -0.06
    CHIP
    -0.06
    legs
    -0.06
    rss
    -0.06
    ode
    -0.06
    trade
    -0.06
    POSITIVE LOGITS
    yard
    0.09
    hardt
    0.07
    abor
    0.07
    ill
    0.07
    enco
    0.07
    ëĭī
    0.07
    928
    0.06
    ĵ
    0.06
    eldorf
    0.06
    cko
    0.06
    Activations Density 0.013%

    No Known Activations