© 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 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. 130405
    Prev
    Next
    INDEX
    Explanations

    references to medical supplies or the context of healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text segments that provide grammatical connections between phrases or clarify relationships between elements in a sentence, often serving as essential glue that maintains coherence in the document.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    #
    -0.06
    etc
    -0.06
    yonel
    -0.06
    ADDE
    -0.06
     [âĢ¦
    -0.06
     nackte
    -0.06
     erotische
    -0.06
     kür
    -0.06
    reste
    -0.06
    conde
    -0.06
    POSITIVE LOGITS
     latter
    0.08
     ê·¸ëłĩ
    0.08
    .)↵↵↵↵
    0.07
    éf
    0.07
    .vertx
    0.07
    .dataTables
    0.07
    ãĥ³ãĥĶ
    0.07
    éĿ©
    0.07
    iá»ĥu
    0.07
    ़à¥į
    0.07
    Activations Density 3.778%

    No Known Activations