© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 59468
    Prev
    Next
    INDEX
    Explanations

    strong mentions of Hartford and references to medical institutions or procedures

    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
    eren
    -0.07
    ardi
    -0.07
    prav
    -0.07
    gado
    -0.07
    gli
    -0.07
    erdem
    -0.07
    cz
    -0.07
    gaard
    -0.07
    essen
    -0.07
    branches
    -0.07
    POSITIVE LOGITS
    ificial
    0.08
    igan
    0.07
    uell
    0.07
    isans
    0.07
    reuse
    0.07
    uelle
    0.07
    wood
    0.07
    çħ§
    0.06
    alom
    0.06
    istry
    0.06
    Activations Density 0.005%

    No Known Activations