© 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. 76048
    Prev
    Next
    INDEX
    Explanations

    references to a specific jail or correctional facility

    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
    afs
    -0.07
    LOSE
    -0.07
    zar
    -0.06
    iser
    -0.06
    qui
    -0.06
     signalling
    -0.06
    isers
    -0.06
    ä¿
    -0.06
    ummer
    -0.06
     Tham
    -0.06
    POSITIVE LOGITS
    agues
    0.07
     Records
    0.06
    _records
    0.06
    herits
    0.06
     records
    0.06
     mug
    0.06
    records
    0.06
    orno
    0.06
     bonds
    0.06
    Lookup
    0.06
    Activations Density 0.004%

    No Known Activations