© 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. 55329
    Prev
    Next
    INDEX
    Explanations

    geographic names and references related to New England

    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
    uml
    -0.07
    ikal
    -0.06
     Wagner
    -0.06
    oun
    -0.06
     latter
    -0.06
    Ä±ÅŁÄ±k
    -0.06
    .Transactional
    -0.06
    apsed
    -0.06
    rais
    -0.06
    áš
    -0.06
    POSITIVE LOGITS
    /New
    0.09
    ighth
    0.08
    lings
    0.08
    igits
    0.07
    swire
    0.07
    edly
    0.07
     Zealand
    0.07
    tg
    0.07
    ensex
    0.07
    lement
    0.07
    Activations Density 0.035%

    No Known Activations