© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 59000
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or terms related to legal documents and programming language elements

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

    Programming-related identifiers, variable names, and technical components within software code and documentation.

    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
    peÄį
    -0.08
    .Reporting
    -0.08
    öyle
    -0.08
    peria
    -0.08
    raud
    -0.07
    tones
    -0.07
    .MixedReality
    -0.07
    Ìģt
    -0.07
    âĢĮâĢĮ
    -0.07
    ebi
    -0.07
    POSITIVE LOGITS
    615
    0.06
    airs
    0.06
    uit
    0.06
    ern
    0.06
    583
    0.05
    -FIRST
    0.05
    als
    0.05
    Ùĭا
    0.05
    ilde
    0.05
     Cutting
    0.05
    Activations Density 0.005%

    No Known Activations