© 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. 130647
    Prev
    Next
    INDEX
    Explanations

    mentions of medical conditions and survival experiences

    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
    osg
    -0.07
    athy
    -0.07
    493
    -0.07
    avr
    -0.07
    vertis
    -0.07
    ricks
    -0.07
    IRM
    -0.06
    .requests
    -0.06
    echa
    -0.06
    _pb
    -0.06
    POSITIVE LOGITS
     subsequently
    0.08
     thereafter
    0.07
     hospital
    0.07
     afterwards
    0.06
     Boom
    0.06
     subsequent
    0.06
     then
    0.06
     ansch
    0.06
     hospitals
    0.06
     recuper
    0.06
    Activations Density 0.030%

    No Known Activations