© 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. 17-LLAMASCOPE-RES-131K
    6. 70650
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure related to defining types and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Hud
    -0.07
    nám
    -0.06
    igg
    -0.06
    antas
    -0.06
     Tamb
    -0.06
     Bak
    -0.06
     dom
    -0.06
     k
    -0.06
     fac
    -0.05
     pie
    -0.05
    POSITIVE LOGITS
    -fontawesome
    0.08
    ncia
    0.07
    ooter
    0.07
    kaar
    0.07
     âĹĦ
    0.07
    _<?
    0.06
    endoza
    0.06
    avanaugh
    0.06
    aler
    0.06
    ç´
    0.06
    Activations Density 0.001%

    No Known Activations