© 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. 17-LLAMASCOPE-RES-131K
    6. 94474
    Prev
    Next
    INDEX
    Explanations

    names and terms related to prominent individuals and their influence or actions

    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
    naire
    -0.07
    oria
    -0.07
    ka
    -0.07
    enc
    -0.07
    eat
    -0.07
    rig
    -0.07
    itemap
    -0.07
    ular
    -0.07
    jon
    -0.07
    getMock
    -0.07
    POSITIVE LOGITS
     har
    0.09
     Har
    0.07
    agus
    0.07
    assing
    0.07
    оваÑĤелÑĮ
    0.07
    Har
    0.06
    WEEN
    0.06
    apan
    0.06
    har
    0.06
    wood
    0.06
    Activations Density 0.031%

    No Known Activations