© 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. 15-LLAMASCOPE-RES-131K
    11. 61294
    Prev
    Next
    INDEX
    Explanations

    references to annual events and festivals

    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
    brick
    -0.08
    oku
    -0.08
    gio
    -0.07
    åĽ½äº§
    -0.07
    oji
    -0.06
    ése
    -0.06
    WND
    -0.06
    oa
    -0.06
    mediate
    -0.06
    toBeDefined
    -0.06
    POSITIVE LOGITS
     traditions
    0.07
     Bac
    0.07
    kre
    0.07
     bac
    0.06
     tob
    0.06
     tradition
    0.06
     Patton
    0.06
    uploaded
    0.06
     ham
    0.06
    trad
    0.06
    Activations Density 0.004%

    No Known Activations