© 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. 15-LLAMASCOPE-RES-131K
    6. 90651
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software configuration and integration

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

    Technical documentation fragments, particularly section headings and project names in software documentation, often in markdown format.

    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
    ailed
    -0.06
    angler
    -0.06
     syndrome
    -0.05
    getSingleton
    -0.05
    ou
    -0.05
    .sdk
    -0.05
     Boutique
    -0.05
    à¸ļà¸Ĺ
    -0.05
     BindingFlags
    -0.05
    rana
    -0.05
    POSITIVE LOGITS
    clave
    0.07
    iyet
    0.07
    .rs
    0.07
    aset
    0.07
    .nr
    0.07
    claimer
    0.07
     hát
    0.07
    γÏĩ
    0.06
     Äijây
    0.06
    ITTE
    0.06
    Activations Density 0.090%

    No Known Activations