© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 635
    Prev
    Next
    INDEX
    Explanations

    structured data elements or metadata in a document

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

    JSON/markup syntax elements including: field delimiters (":"), null values, JSON array/object brackets, numeric values (0, 1), and style/display attributes in HTML. These elements appear consistently in structured data representations like JSON objects or HTML code.

    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
    agna
    -0.08
    oogle
    -0.07
    hausen
    -0.06
    APO
    -0.06
    й
    -0.06
    itten
    -0.06
    ++.
    -0.06
     Wise
    -0.06
     alo
    -0.06
     Trading
    -0.06
    POSITIVE LOGITS
    .undefined
    0.08
    vern
    0.07
    LING
    0.07
    ("{\"
    0.07
    undefined
    0.06
    ÏĮÏģ
    0.06
    _learn
    0.06
     bek
    0.06
    .cloudflare
    0.06
    ãĥ³ãĥĩ
    0.06
    Activations Density 0.572%

    No Known Activations