© 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. 9-LLAMASCOPE-RES-131K
    11. 95071
    Prev
    Next
    INDEX
    Explanations

    instances of the word "open" and its variations, indicating a focus on actions related to accessing or initializing files or programs

    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
    ima
    -0.07
    ena
    -0.07
    ivet
    -0.06
    hed
    -0.06
     overd
    -0.06
    inas
    -0.06
    eneg
    -0.06
    isku
    -0.06
    ene
    -0.06
     Lions
    -0.06
    POSITIVE LOGITS
     GetLastError
    0.08
    жи
    0.07
    èµ·æĿ¥
    0.07
    713
    0.07
    ogany
    0.07
     Kund
    0.07
     Hammond
    0.07
    \Collections
    0.06
    æľ
    0.06
    ìĦ¸
    0.06
    Activations Density 0.008%

    No Known Activations