© 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. 75718
    Prev
    Next
    INDEX
    Explanations

    expressions related to routine and familiarity

    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
    retch
    -0.06
    slaught
    -0.06
    obody
    -0.06
    ListAdapter
    -0.06
     THEN
    -0.06
    zyst
    -0.05
     dein
    -0.05
    iyim
    -0.05
    wi
    -0.05
    adin
    -0.05
    POSITIVE LOGITS
     whenever
    0.11
    always
    0.11
     вÑģегда
    0.10
     always
    0.09
     Whenever
    0.09
     regularly
    0.09
    Whenever
    0.09
     siempre
    0.08
     ALWAYS
    0.08
     sempre
    0.08
    Activations Density 0.042%

    No Known Activations