© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 88118
    Prev
    Next
    INDEX
    Explanations

    repeated instances of particular prefixes or suffixes in words

    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
    y
    -0.10
    ying
    -0.07
    ling
    -0.06
    sb
    -0.06
    aqu
    -0.06
    auf
    -0.06
    geist
    -0.06
    cy
    -0.06
    sburg
    -0.06
    sd
    -0.06
    POSITIVE LOGITS
     nues
    0.08
    \Collections
    0.08
    Deferred
    0.07
    æ´»
    0.07
    Printf
    0.07
    endra
    0.06
    جÙĦ
    0.06
    _dma
    0.06
    .rl
    0.06
    ichni
    0.06
    Activations Density 0.001%

    No Known Activations