© 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. 88812
    Prev
    Next
    INDEX
    Explanations

    words related to collaborative projects involving digital encyclopedias

    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
    etas
    -0.07
    roi
    -0.07
     rug
    -0.06
    acas
    -0.06
     Ober
    -0.06
     CIM
    -0.06
    lease
    -0.06
    _foreign
    -0.06
    onte
    -0.06
    ems
    -0.06
    POSITIVE LOGITS
     enc
    0.08
     Enc
    0.08
    .wikipedia
    0.08
    pedia
    0.07
    owi
    0.07
     encyclopedia
    0.07
    ç¶Ń
    0.07
    -edit
    0.07
    anzi
    0.07
    ENCY
    0.07
    Activations Density 0.013%

    No Known Activations