© 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. 127142
    Prev
    Next
    INDEX
    Explanations

    unique or playful spellings of food-related terms and ingredients

    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
    åĩĮ
    -0.08
     каÑģ
    -0.07
    edb
    -0.07
    beb
    -0.07
    BuilderInterface
    -0.07
    urger
    -0.07
    iets
    -0.07
    еÑĢеж
    -0.06
     èIJ
    -0.06
    legg
    -0.06
    POSITIVE LOGITS
    arto
    0.06
     pronounced
    0.06
    ·
    0.05
    Äĵ
    0.05
    brid
    0.05
     (;;
    0.05
     Cir
    0.05
    erville
    0.05
    kit
    0.05
    umas
    0.05
    Activations Density 0.004%

    No Known Activations