© 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. 105620
    Prev
    Next
    INDEX
    Explanations

    terms related to government, legal, and institutional entities

    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
    isol
    -0.08
    inea
    -0.08
    سÙĩ
    -0.08
    ále
    -0.08
    :System
    -0.08
    istrovstvÃŃ
    -0.08
    gré
    -0.08
    inue
    -0.08
    INET
    -0.08
    stem
    -0.07
    POSITIVE LOGITS
     Kr
    0.06
    cs
    0.06
    -Compatible
    0.05
    escription
    0.05
    -scalable
    0.05
     Readonly
    0.05
     Cohen
    0.05
     Wr
    0.05
     Doe
    0.05
     Telegraph
    0.05
    Activations Density 0.056%

    No Known Activations