© 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 EvalsExportsinterp-engineNEWAPI 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. 17985
    Prev
    Next
    INDEX
    Explanations

    concepts related to advanced material science and self-assembly processes

    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
     Gor
    -0.06
    Docs
    -0.06
    mana
    -0.06
    bote
    -0.06
     âĹĦ
    -0.06
    azio
    -0.06
     blitz
    -0.06
     Job
    -0.06
    Utils
    -0.06
    omik
    -0.06
    POSITIVE LOGITS
     actu
    0.09
    á»Ĩ
    0.07
     Blockly
    0.07
     imb
    0.07
    .annot
    0.06
    åİ
    0.06
     Whitney
    0.06
    PIO
    0.06
     tens
    0.06
    PropertyName
    0.06
    Activations Density 0.004%

    No Known Activations