© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71811
    Prev
    Next
    INDEX
    Explanations

    occurrences of code-related terminology and function structures

    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
    ãĥ¬ãĤ¹
    -0.08
    нам
    -0.07
    jspx
    -0.07
    дап
    -0.07
    asin
    -0.07
    agrid
    -0.07
    AdapterFactory
    -0.07
     kaydet
    -0.07
    ارس
    -0.07
    ãĥ©ãĤ¹
    -0.07
    POSITIVE LOGITS
     other
    0.07
     others
    0.06
     cur
    0.06
    other
    0.06
     setSelected
    0.06
    enen
    0.06
     oc
    0.06
    annies
    0.06
     selected
    0.06
     correspond
    0.06
    Activations Density 0.012%

    No Known Activations