© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82529
    Prev
    Next
    INDEX
    Explanations

    words related to ancient Egyptian culture and hieroglyphics

    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
    å©Ĩ
    -0.07
    cs
    -0.06
    uff
    -0.06
    ستÙĩ
    -0.06
     Pruitt
    -0.06
    arians
    -0.06
    avo
    -0.06
    690
    -0.06
     stump
    -0.06
    .getSelected
    -0.05
    POSITIVE LOGITS
    perm
    0.08
    oti
    0.07
    athing
    0.07
    SystemService
    0.07
    ForResource
    0.06
     latin
    0.06
    pend
    0.06
    iday
    0.06
    fü
    0.06
    EGA
    0.06
    Activations Density 0.003%

    No Known Activations