© 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. 70585
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions

    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
    .tap
    -0.08
    åĦĢ
    -0.07
    ãĥ¼ãĥŀ
    -0.07
    obra
    -0.07
    zew
    -0.07
     Tempo
    -0.07
    /frontend
    -0.07
    ayment
    -0.07
    ntax
    -0.07
    obraz
    -0.07
    POSITIVE LOGITS
    anges
    0.07
    rag
    0.07
    ucher
    0.07
    ods
    0.07
    vir
    0.06
    åıİ
    0.06
    eller
    0.06
     sp
    0.06
     PoÄįet
    0.06
    1
    0.06
    Activations Density 0.049%

    No Known Activations