© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90616
    Prev
    Next
    INDEX
    Explanations

    references to deep learning and its applications in medical image classification

    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
    quam
    -0.08
    ellites
    -0.07
    itemid
    -0.07
    bios
    -0.07
    .XR
    -0.07
    .absolute
    -0.07
    leo
    -0.07
    کات
    -0.07
    ellite
    -0.06
    uchar
    -0.06
    POSITIVE LOGITS
    å±
    0.07
     newer
    0.07
    anken
    0.06
    šak
    0.06
    arti
    0.06
     Machine
    0.06
    ewn
    0.06
     deep
    0.06
     Moore
    0.06
    ImageData
    0.06
    Activations Density 0.033%

    No Known Activations