© 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 EvalsExportsinterp-engineNEWAPI 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. 92148
    Prev
    Next
    INDEX
    Explanations

    metadata and structured data elements

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

    The equals sign or colon-number sequence in timestamps, dates, or code syntax, typically appearing in URLs, function parameters, or blog post metadata.

    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
     Beled
    -0.08
     yacc
    -0.07
    ivery
    -0.07
    åľ¨çº¿éĺħ读
    -0.07
    /antlr
    -0.07
     {[
    -0.07
    ersions
    -0.07
    .spark
    -0.07
    azz
    -0.07
     lekker
    -0.07
    POSITIVE LOGITS
    hora
    0.06
    hazi
    0.05
     parti
    0.05
     Sta
    0.05
    åħ¥ãĤĬ
    0.05
     wishes
    0.05
    ÄŁe
    0.05
     visible
    0.05
     com
    0.05
    unto
    0.05
    Activations Density 0.111%

    No Known Activations