© 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. 120047
    Prev
    Next
    INDEX
    Explanations

    references to Springfield and related locations

    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
     ling
    -0.07
    avad
    -0.06
    thon
    -0.06
    vation
    -0.06
    pector
    -0.06
    AMED
    -0.06
    -0.06
    ephir
    -0.06
    naments
    -0.06
     Mellon
    -0.06
    POSITIVE LOGITS
    zeug
    0.09
    uality
    0.09
    zee
    0.07
    leh
    0.07
    arians
    0.07
    /OR
    0.07
    ously
    0.07
    Äįek
    0.07
    ResourceId
    0.07
    ople
    0.07
    Activations Density 0.003%

    No Known Activations