© 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. 90594
    Prev
    Next
    INDEX
    Explanations

    code-related structures and syntactic elements

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

    Programming code syntax elements, particularly function definitions, method calls, and their arguments, often appearing at boundaries of code blocks.

    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
    rtl
    -0.08
    conti
    -0.08
    contri
    -0.07
    oner
    -0.07
    gang
    -0.07
    ÙĪØ²ÛĮ
    -0.07
    nite
    -0.07
    ogan
    -0.07
    assel
    -0.07
    Äħż
    -0.07
    POSITIVE LOGITS
    -Ray
    0.06
    alk
    0.06
    584
    0.06
     ifndef
    0.06
     Kahn
    0.06
     Pap
    0.06
    uchi
    0.05
     Tư
    0.05
     Stuff
    0.05
    Kit
    0.05
    Activations Density 0.004%

    No Known Activations