© 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. 107075
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to significant achievements or noteworthy occurrences

    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
    723
    -0.07
    zh
    -0.06
    queda
    -0.06
    ught
    -0.06
    onds
    -0.06
    opt
    -0.06
    ikes
    -0.06
    iris
    -0.06
    circle
    -0.06
    irsch
    -0.06
    POSITIVE LOGITS
    çļĦæĺ¯
    0.09
     nữa
    0.08
    ë¡ľëĬĶ
    0.08
     is
    0.07
    å°±æĺ¯
    0.07
     εÏĢίÏĥηÏĤ
    0.07
    åĥıæĺ¯
    0.07
     include
    0.07
    mino
    0.07
    주ëĬĶ
    0.06
    Activations Density 0.032%

    No Known Activations