© 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. 79147
    Prev
    Next
    INDEX
    Explanations

    references to specific New Year's celebrations and the related year numbers

    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
    oda
    -0.07
    orea
    -0.07
    bast
    -0.06
    licer
    -0.06
    жив
    -0.06
    nun
    -0.06
    ernes
    -0.06
    odo
    -0.06
    ODO
    -0.06
     meis
    -0.06
    POSITIVE LOGITS
    son
    0.07
    ls
    0.07
    ly
    0.06
    oft
    0.06
     Jam
    0.06
    ’n
    0.06
    tridge
    0.06
    theless
    0.06
    _PACK
    0.06
    SGlobal
    0.06
    Activations Density 0.002%

    No Known Activations