© 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. 58880
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare management and chronic disease support

    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
    ndx
    -0.08
    Unnamed
    -0.07
    afia
    -0.07
    spb
    -0.07
    llib
    -0.07
    esium
    -0.06
    _operand
    -0.06
    hod
    -0.06
     Rig
    -0.06
    hoot
    -0.06
    POSITIVE LOGITS
     discharged
    0.07
     heart
    0.07
    ÙĤاÙħ
    0.07
    ÐŁÐļ
    0.07
     discharge
    0.07
     dial
    0.07
     home
    0.07
     SCRIPT
    0.06
     frequent
    0.06
    康
    0.06
    Activations Density 0.034%

    No Known Activations