© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 88781
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms related to programming and software development

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

    Python code patterns, particularly function definitions, class definitions, and method calls with their associated syntax like parameter assignment (=), return statements, and property decorators in programming contexts. The patterns often include method declarations, variable assignments, and Python-specific constructs.

    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
    zew
    -0.06
    uis
    -0.06
     pearl
    -0.06
     Aph
    -0.06
    omp
    -0.06
    åĽ
    -0.06
     Pear
    -0.06
     refere
    -0.06
    airy
    -0.06
     Opport
    -0.06
    POSITIVE LOGITS
    Vectorizer
    0.07
    elif
    0.07
     ast
    0.06
    opleft
    0.06
    ãģ¯ãģļ
    0.06
    pike
    0.06
    (None
    0.06
    allen
    0.06
    ä¹Ĥ
    0.06
     *č↵
    0.06
    Activations Density 0.266%

    No Known Activations