© 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. 61610
    Prev
    Next
    INDEX
    Explanations

    significant actions or events related to church activities and community projects

    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
     recent
    -0.10
     recently
    -0.08
     lately
    -0.07
    recent
    -0.07
    avana
    -0.07
    getti
    -0.07
     similarly
    -0.07
     previous
    -0.07
    _recent
    -0.07
    Recently
    -0.07
    POSITIVE LOGITS
     accordingly
    0.12
     böylece
    0.08
     thus
    0.08
     Accordingly
    0.08
    thus
    0.07
    wares
    0.07
    æŃ£å¼ı
    0.07
     nakonec
    0.07
     Thus
    0.07
     duly
    0.07
    Activations Density 0.031%

    No Known Activations