© 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. 87065
    Prev
    Next
    INDEX
    Explanations

    descriptors related to graphics and visual quality in video games

    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
     serial
    -0.06
     ends
    -0.06
    :
    -0.06
     Ending
    -0.06
     pute
    -0.06
     Ends
    -0.05
     Armed
    -0.05
     Ej
    -0.05
     Fiction
    -0.05
    vida
    -0.05
    POSITIVE LOGITS
     jadx
    0.09
    PEG
    0.08
     Dün
    0.08
    buie
    0.08
    rys
    0.08
    ãģĵãĤĵãģ«
    0.08
     bacheca
    0.07
    ervo
    0.07
    corlib
    0.07
    slaught
    0.07
    Activations Density 0.019%

    No Known Activations